Nearly half of C2 malware bypasses DNS by connecting directly to IP addresses. Zero trust IP enforcement secures networks against these threats.
The post Almost Half of Malware Samples Communicate Direct to IP appeared first on Unit 42.
Researchers have described a campaign that delivers a remote access Trojan (RAT) called AtlasRAT through a fake Flash Player installer.
People still go looking for “Flash player” because a surprising amount of content and software was built around Flash and never properly migrated. Users often just want a quick way to get those old sites, games, or business apps working again.
The underlying problem is that Adobe ended support for Flash Player on December 31, 2020, and actively blocks Flash content from running in the official player.
Attackers know some people will still search for Flash to run a game or a business app, so they wrap their malware in a fake Flash‑related installer that looks familiar and legitimate.
That’s likely why the AtlasRAT infection chain starts with a Delphi executable named FlashPlay.Exe, masquerading as an “AGE Flash Player” installer. The first-stage loader runs entirely in memory and reconstructs additional payloads instead of dropping obvious files to disk, a technique often referred to as fileless malware.
The final payload (MainDll.Dll) uses a self‑signed certificate spoofing CN=update.Microsoft.Com to initialize Transport Layer Security (TLS) client communication and encrypts Command and Control (C2) traffic.
A self‑signed certificate means the owner signs with their own key instead of a trusted certificate authority (CA). That means an attacker can create a certificate claiming to be update.microsoft.com or google.com, even though they don’t control those domains. A web browser would reject such a certificate with a warning. Custom malware, however, can simply ignore the operating system’s trust checks and use it to set up encrypted C2.
Once AtlasRAT is installed, the operator gains long‑term remote control of the infected Windows system with capabilities including:
Based on historical data, the researchers suspect that AtlasRAT is a reusable framework or commercial offering rather than a one-off tool used by a single group.
When looking for apps and software to perform a specific task, remember that cybercriminals often exploit popular searches in semi-targeted attacks. In previous campaigns, for example, AtlasRAT has also been distributed as a fake VPN installer.
Some tips to keep this RAT, and others, off your computer:
From reporting threats to removing them.
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
Researchers have described a campaign that delivers a remote access Trojan (RAT) called AtlasRAT through a fake Flash Player installer.
People still go looking for “Flash player” because a surprising amount of content and software was built around Flash and never properly migrated. Users often just want a quick way to get those old sites, games, or business apps working again.
The underlying problem is that Adobe ended support for Flash Player on December 31, 2020, and actively blocks Flash content from running in the official player.
Attackers know some people will still search for Flash to run a game or a business app, so they wrap their malware in a fake Flash‑related installer that looks familiar and legitimate.
That’s likely why the AtlasRAT infection chain starts with a Delphi executable named FlashPlay.Exe, masquerading as an “AGE Flash Player” installer. The first-stage loader runs entirely in memory and reconstructs additional payloads instead of dropping obvious files to disk, a technique often referred to as fileless malware.
The final payload (MainDll.Dll) uses a self‑signed certificate spoofing CN=update.Microsoft.Com to initialize Transport Layer Security (TLS) client communication and encrypts Command and Control (C2) traffic.
A self‑signed certificate means the owner signs with their own key instead of a trusted certificate authority (CA). That means an attacker can create a certificate claiming to be update.microsoft.com or google.com, even though they don’t control those domains. A web browser would reject such a certificate with a warning. Custom malware, however, can simply ignore the operating system’s trust checks and use it to set up encrypted C2.
Once AtlasRAT is installed, the operator gains long‑term remote control of the infected Windows system with capabilities including:
Based on historical data, the researchers suspect that AtlasRAT is a reusable framework or commercial offering rather than a one-off tool used by a single group.
When looking for apps and software to perform a specific task, remember that cybercriminals often exploit popular searches in semi-targeted attacks. In previous campaigns, for example, AtlasRAT has also been distributed as a fake VPN installer.
Some tips to keep this RAT, and others, off your computer:
From reporting threats to removing them.
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
Leveraging legitimate software is one of cybercriminals’ tactics of choice, with remote management tools ranking among their top tools. A recent example involves the remote administration utility ScreenConnect. It’s designed for IT support teams to troubleshoot systems and configure software seamlessly in the background. However, when weaponized by threat actors, ScreenConnect becomes a versatile attack vehicle used to harvest data, deploy malware, and move laterally across corporate networks.
During a recent incident detected by Kaspersky Managed Detection and Response, our experts identified an attempt to use ScreenConnect in an attack. This allowed a detailed study of how attackers used this application in a large-scale malware distribution campaign. The following breakdown illustrates the mechanics of ScreenConnect-assisted attacks, and outlines key strategies to defend your organization against them.
In the campaign analyzed by our experts, the attackers bundled ScreenConnect with legitimate free business software. They established a network of phishing websites to spoof popular tools, including OBS Studio, DS4Windows, DNS Jumper, Glary Utilities, Bandizip, Process Hacker, and others.
These rogue websites featured high-quality designs that could be taken for the official pages, making them highly convincing to unsuspecting users. Once the victim clicks the download button for the software, an archive is downloaded to their computer that contains additional files alongside the requested application:
Launching the renamed file disguised as the app installer triggers DLL sideloading of a malicious library. This library silently runs the ScreenConnect installation without restarting the system, while using the standard Windows installer to set up the software the user originally tried to install.
The attackers used search engine optimization techniques to drive traffic to their fake websites. As a result, these malicious pages appeared at the top of search results for certain free software utilities on major search engines.
Our experts discovered over 90 domain names translated into more than 10 different languages. While most of these websites targeted English, Russian, and Chinese speakers, several domains catered to German, French, Spanish, Arabic, and other regional audiences.
A detailed analysis of the IP addresses and associated spoofed domains is available in our technical research article on Securelist, along with full indicators of compromise.
In this campaign, attackers leveraged ScreenConnect to generate and execute malicious scripts on victim machines. These scripts served several key functions: they created exclusions for specific drives, directories, and processes within Windows Defender, disabled the User Account Control (UAC) security mechanism, and delivered and deployed AsyncRAT – a remote access Trojan.
To maintain persistence, the scripts configured a Windows scheduled task to run the malicious code at preset intervals. AsyncRAT then established a connection with the attackers’ command-and-control server to receive further instructions.
The primary objective of this campaign appears to be gaining unauthorized access to enterprise systems, likely to then resell it on cybercrime marketplaces.
Although ScreenConnect in and of itself is a legitimate tool, its presence poses a security risk to corporate environments. Consequently, Kaspersky security solutions detect this application as not-a-virus:HEUR:RemoteAdmin.MSIL.ConnectWise.gen.
Security teams should implement the following controls:
As noted previously, this campaign was originally detected through the Kaspersky Managed Detection and Response service, which can be employed to protect against such threats.
In February 2026, we discovered a set of malicious activities that had been ongoing since late 2025. These activities involved a RAT module written in Go with proxy capabilities, which served as the main stage of the attack. The attack targeted government and diplomatic entities in Southeast Asia and showed a level of sophistication that caught our attention.
During the attack, the main malware, dubbed GoSerpent, received an encrypted argument and started communicating with a remote server. It was also used to deploy further malicious tools to collect sensitive data and dump credentials on the system.
Monitoring the activities of this threat actor revealed that in May 2026, they came back with an evolved set of malicious tools: a new RAT and proxy tool, Stowaway, which resembled the initial malware, as well as an additional stealthy tool to exfiltrate sensitive data collected in the previous few months through network shares.
We found earlier versions of the GoSerpent backdoor used since 2021 against victims in Southeast Asia with relatively simpler code that received command-line arguments in plain text. Even though the newer variant is stealthier, the attackers continued using the simpler version alongside the latest one in their recent attacks.
What makes this threat particularly concerning is the strategic deployment of various tools with sophisticated data collection and exfiltration capabilities.
In this article, we introduce the malicious tools uncovered by us, which have been used since late 2025.
The initial phase of the attacks involved deployment of the GoSerpent backdoor, followed by additional malicious tools. During this phase, the main goal was to collect sensitive files and store them for future exfiltration, which was done by a data collecting tool, ThumbcacheService. The attackers also needed system credentials to exfiltrate the collected data through network drives at a later stage. This was achieved through a number of credential dumping tools deployed in this phase via the GoSerpent backdoor.
The primary weapon in this campaign is the GoSerpent backdoor, a sophisticated Go-based remote access Trojan that has been active since at least 2021, with the most recent variant deployed in 2026.
This malware receives encrypted and base64-encoded command-line arguments containing a C2 server address and communication password, which are decrypted using AES-CBC mode with a fixed IV (31323334353637383930616263646566) and keys derived from predefined strings.
The backdoor connects to command-and-control servers using ChaCha20 encryption for communications, with the SHA256 hash of the communication password serving as the encryption key.
GoSerpent supports multiple C2 commands by receiving special command values. The commands include the following:
| Command | Symbol (as derived from corresponding function names) | Description |
| 2BA1 | Sync | Respond to the server to show the infection is active |
| 3BA2 | Exit | Exit process |
| 4BA3 | Ls | Start listening on a port |
| 5BA4 | Connect | Connect to a remote server |
| 6BA5 | Hello | Create a shell on the infected machine |
| 7BA6 | Ul | Upload a file or directory to the server |
| 8BA7 | Dl | Download from the server |
| 9BA8 | Ss5 | Start a SOCKS5 proxy on the infected machine |
| ABA9 | Cl | Close a listening port |
| CBAB | RF | Forward to a connected node |
GoSerpent can establish SOCKS5 proxy servers to route traffic through compromised hosts, enabling attackers to access other networks while masking their true IP addresses. The backdoor is capable of deploying additional malicious tools, including ThumbcacheService for file collection, Mimikatz for credential dumping, and QuarksDumpLocalHash for local account password hash extraction. The malware exhibits strong persistence mechanisms and uses filenames that mimic legitimate system processes such as lass.exe and updates.exe to evade detection.
McMx is a basic Go-based proxy and remote access tool that represents a simpler variant of the GoSerpent backdoor, apparently compiled from a different GitHub repository path.
Unlike the latest variant of GoSerpent, which uses encrypted command-line arguments, McMx receives input parameters from text files in plaintext format — in a way that resembles older versions of GoSerpent. The malware features similar function names with apparent typos present in both tools.
Before executing McMx, attackers manipulate batch files to generate configuration files containing C2 parameters. The patterns observed show the use of echo commands to create configuration files with parameters like remote host addresses, ports, and secret keys. The McMx malware is then deployed with this configuration.
The tool shares core functionalities with GoSerpent, including:
Following initial deployment of the GoSerpent backdoor, attackers typically wait several days before utilizing it to download and execute additional malware components for data collection and credential dumping.
ThumbcacheService is a malicious DLL deployed as a Windows service that functions as a sophisticated file collection mechanism within the GoSerpent ecosystem. The malware employs XOR encryption with a single-byte key of 0x13 for string obfuscation. It decrypts embedded strings and creates a database file named thumbcache_605a.db in the C:\Users\Public\ directory to store collected sensitive files. It specifically targets documents with the following extensions: .doc, .docx, .pdf, .xls and .xlsx.
The targeted files are then archived using 7-Zip and protected with a predefined password @vx0a9n5W2M0c3D6.#, enforcing a 20MB size limit for archives.
The malicious service also monitors the $Recycle.Bin directory for deleted files with the extensions of interest, ensuring comprehensive data collection.
The threat actor deploys the following tools via GoSerpent backdoor to dump credentials:
These tools work together to maximize information extraction from compromised systems. The stolen credentials were used in later stages of the attack to facilitate the exfiltration of sensitive files collected by ThumbcacheService.
After the initial phase of the malware deployments, the attackers allowed a few weeks for the ThumbcacheService to silently collect sensitive files without exfiltrating them. In the meantime, the credential dumping tools also continued to steal credentials. In May 2026, the threat actor came back with a set of new tools. The main malware of this round of activity was another Go-based RAT and proxy tool, Stowaway. It was used to deploy the two-stage data exfiltration tool TmcLoader/TmcPayload, which was the last piece of the data theft puzzle.
Stowaway is a proxy and remote access tool compiled from an open-source framework with customized functions to make the infection stealthier. This malware features both network admin and agent capabilities, enabling attackers to establish chained proxy paths across multiple hosts with the following functionalities:
Communications are transported over TCP, HTTP, or WebSocket channels protected by AES-256-GCM or TLS encryption.
As the next step, the attackers deliver two files to the victim machine via Stowaway:
Login
{BBF061R2-BE25-4F6D-8B2D-1A6A39C3FSA2}.db — an encrypted configuration fileTmcLoader is a stealthy C++ loader module registered as a Windows service. The malware embeds an encrypted payload dubbed TmcPayload within its .data section, which is decrypted and loaded into the memory space of the svchost process to maintain persistence and avoid detection.
TmcLoader employs dynamic API resolution through a circular XOR encryption, where each byte is XORed with the value of the subsequent byte, combined with Base64 encoding for string obfuscation to hide API names.
The loader creates a unique event to prevent multiple infections on the same system. After that, it extracts and decrypts the embedded TmcPayload. This payload component is responsible for exfiltrating sensitive data from the victim’s machine.
TmcPayload generates a file path from an obfuscated string: C:\Users\Public\Libraries\{BBF061R2-BE25-4F6D-8B2D-1A6A39C3FSA2}.db.
It then checks for the existence of this configuration file. If the file doesn’t exist, it delays execution for a random period of time before rechecking. The configuration file contains encrypted network share credentials and destination paths for data exfiltration. It specifically references the thumbcache_605a.db file created by ThumbcacheService as the file to be exfiltrated, demonstrating the integrated nature of the attack chain.
What distinguishes this threat actor’s approach is the deliberate integration between different components of their toolset. The chain from ThumbcacheService to TmcLoader/TmcPayload demonstrates sophisticated operational planning:
thumbcache_605a.db database file.thumbcache_605a.db.This integration shows that the threat actor has carefully orchestrated their tools to work together seamlessly, ensuring that data collected by one component is available for exfiltration by another component.
The malware operators leverage legitimate hosting providers, including Alibaba Cloud and UCLOUD HK, for their command-and-control infrastructure. The use of legitimate hosting platforms demonstrates operational security awareness, making detection more challenging.
The technical similarities between GoSerpent and the newer Stowaway tools strongly suggest the threat actor’s deep familiarity with network proxy technologies. The consistent use of legitimate domain names as secret keys, with GoSerpent employing www.microsoft.com and www.spacex.com and Stowaway utilizing github.code, indicates a standardized operational methodology.
While the exact attribution of the GoSerpent campaign remains uncertain, there are indications of a potential link to the TetrisPhantom threat actor. The similarities in victim targeting, technical capabilities, and operational methodologies suggest a possible connection. However, further investigation is necessary to confirm this association.
The GoSerpent campaign represents a sophisticated and evolving threat to government and diplomatic entities in Southeast Asia. The threat actor’s use of customized tools, such as the GoSerpent backdoor, Stowaway, and TmcLoader, demonstrates a high degree of technical expertise and operational planning. The integration of these tools to collect and exfiltrate sensitive data highlights the actor’s focus on long-term access and intelligence gathering. As the threat landscape continues to shift, it is essential for organizations to remain vigilant and implement robust security measures to detect and prevent such attacks. By understanding the tactics, techniques, and procedures (TTPs) employed by this threat actor, defenders can better prepare themselves to counter similar threats in the future.
GoSerpent
EBFFD5A76AAA690BCDB922F82E0BACC5
DC506FF7BB72735444FB3703A6BEE6D8
McMx
D6E86BF8A90E9B632ADD5FA495F97FBC
ThumbcacheService
CB6C4C70A3B171FA3404B8E1A3382116
64E9D1950E42BC98486DFD9919463D1C
Stowaway
CBBB6D483737EA3566726E51752DFF40
7F223EE0716CE2AD56F55D3744419449
19F8BEFCB035F52BF70094E6B4F5779A
846EF7C1C7323849B2A778C5E4CDA162
TmcLoader
D08A059E8B815E3B891505BC8777FC28
93A1569D5D5AB2C4761FEDF84F83709E
152.32.160[.]239
8.220.194[.]108
8.220.214[.]132
8.220.209[.]155
8.220.193[.]189
101.36.104[.]87
144.48.6[.]46
103.138.13[.]30
47.80.22[.]58
152.32.222[.]113
43.106.30[.]226
In February 2026, we discovered a set of malicious activities that had been ongoing since late 2025. These activities involved a RAT module written in Go with proxy capabilities, which served as the main stage of the attack. The attack targeted government and diplomatic entities in Southeast Asia and showed a level of sophistication that caught our attention.
During the attack, the main malware, dubbed GoSerpent, received an encrypted argument and started communicating with a remote server. It was also used to deploy further malicious tools to collect sensitive data and dump credentials on the system.
Monitoring the activities of this threat actor revealed that in May 2026, they came back with an evolved set of malicious tools: a new RAT and proxy tool, Stowaway, which resembled the initial malware, as well as an additional stealthy tool to exfiltrate sensitive data collected in the previous few months through network shares.
We found earlier versions of the GoSerpent backdoor used since 2021 against victims in Southeast Asia with relatively simpler code that received command-line arguments in plain text. Even though the newer variant is stealthier, the attackers continued using the simpler version alongside the latest one in their recent attacks.
What makes this threat particularly concerning is the strategic deployment of various tools with sophisticated data collection and exfiltration capabilities.
In this article, we introduce the malicious tools uncovered by us, which have been used since late 2025.
The initial phase of the attacks involved deployment of the GoSerpent backdoor, followed by additional malicious tools. During this phase, the main goal was to collect sensitive files and store them for future exfiltration, which was done by a data collecting tool, ThumbcacheService. The attackers also needed system credentials to exfiltrate the collected data through network drives at a later stage. This was achieved through a number of credential dumping tools deployed in this phase via the GoSerpent backdoor.
The primary weapon in this campaign is the GoSerpent backdoor, a sophisticated Go-based remote access Trojan that has been active since at least 2021, with the most recent variant deployed in 2026.
This malware receives encrypted and base64-encoded command-line arguments containing a C2 server address and communication password, which are decrypted using AES-CBC mode with a fixed IV (31323334353637383930616263646566) and keys derived from predefined strings.
The backdoor connects to command-and-control servers using ChaCha20 encryption for communications, with the SHA256 hash of the communication password serving as the encryption key.
GoSerpent supports multiple C2 commands by receiving special command values. The commands include the following:
| Command | Symbol (as derived from corresponding function names) | Description |
| 2BA1 | Sync | Respond to the server to show the infection is active |
| 3BA2 | Exit | Exit process |
| 4BA3 | Ls | Start listening on a port |
| 5BA4 | Connect | Connect to a remote server |
| 6BA5 | Hello | Create a shell on the infected machine |
| 7BA6 | Ul | Upload a file or directory to the server |
| 8BA7 | Dl | Download from the server |
| 9BA8 | Ss5 | Start a SOCKS5 proxy on the infected machine |
| ABA9 | Cl | Close a listening port |
| CBAB | RF | Forward to a connected node |
GoSerpent can establish SOCKS5 proxy servers to route traffic through compromised hosts, enabling attackers to access other networks while masking their true IP addresses. The backdoor is capable of deploying additional malicious tools, including ThumbcacheService for file collection, Mimikatz for credential dumping, and QuarksDumpLocalHash for local account password hash extraction. The malware exhibits strong persistence mechanisms and uses filenames that mimic legitimate system processes such as lass.exe and updates.exe to evade detection.
McMx is a basic Go-based proxy and remote access tool that represents a simpler variant of the GoSerpent backdoor, apparently compiled from a different GitHub repository path.
Unlike the latest variant of GoSerpent, which uses encrypted command-line arguments, McMx receives input parameters from text files in plaintext format — in a way that resembles older versions of GoSerpent. The malware features similar function names with apparent typos present in both tools.
Before executing McMx, attackers manipulate batch files to generate configuration files containing C2 parameters. The patterns observed show the use of echo commands to create configuration files with parameters like remote host addresses, ports, and secret keys. The McMx malware is then deployed with this configuration.
The tool shares core functionalities with GoSerpent, including:
Following initial deployment of the GoSerpent backdoor, attackers typically wait several days before utilizing it to download and execute additional malware components for data collection and credential dumping.
ThumbcacheService is a malicious DLL deployed as a Windows service that functions as a sophisticated file collection mechanism within the GoSerpent ecosystem. The malware employs XOR encryption with a single-byte key of 0x13 for string obfuscation. It decrypts embedded strings and creates a database file named thumbcache_605a.db in the C:\Users\Public\ directory to store collected sensitive files. It specifically targets documents with the following extensions: .doc, .docx, .pdf, .xls and .xlsx.
The targeted files are then archived using 7-Zip and protected with a predefined password @vx0a9n5W2M0c3D6.#, enforcing a 20MB size limit for archives.
The malicious service also monitors the $Recycle.Bin directory for deleted files with the extensions of interest, ensuring comprehensive data collection.
The threat actor deploys the following tools via GoSerpent backdoor to dump credentials:
These tools work together to maximize information extraction from compromised systems. The stolen credentials were used in later stages of the attack to facilitate the exfiltration of sensitive files collected by ThumbcacheService.
After the initial phase of the malware deployments, the attackers allowed a few weeks for the ThumbcacheService to silently collect sensitive files without exfiltrating them. In the meantime, the credential dumping tools also continued to steal credentials. In May 2026, the threat actor came back with a set of new tools. The main malware of this round of activity was another Go-based RAT and proxy tool, Stowaway. It was used to deploy the two-stage data exfiltration tool TmcLoader/TmcPayload, which was the last piece of the data theft puzzle.
Stowaway is a proxy and remote access tool compiled from an open-source framework with customized functions to make the infection stealthier. This malware features both network admin and agent capabilities, enabling attackers to establish chained proxy paths across multiple hosts with the following functionalities:
Communications are transported over TCP, HTTP, or WebSocket channels protected by AES-256-GCM or TLS encryption.
As the next step, the attackers deliver two files to the victim machine via Stowaway:
{BBF061R2-BE25-4F6D-8B2D-1A6A39C3FSA2}.db — an encrypted configuration fileTmcLoader is a stealthy C++ loader module registered as a Windows service. The malware embeds an encrypted payload dubbed TmcPayload within its .data section, which is decrypted and loaded into the memory space of the svchost process to maintain persistence and avoid detection.
TmcLoader employs dynamic API resolution through a circular XOR encryption, where each byte is XORed with the value of the subsequent byte, combined with Base64 encoding for string obfuscation to hide API names.
The loader creates a unique event to prevent multiple infections on the same system. After that, it extracts and decrypts the embedded TmcPayload. This payload component is responsible for exfiltrating sensitive data from the victim’s machine.
TmcPayload generates a file path from an obfuscated string: C:\Users\Public\Libraries\{BBF061R2-BE25-4F6D-8B2D-1A6A39C3FSA2}.db.
It then checks for the existence of this configuration file. If the file doesn’t exist, it delays execution for a random period of time before rechecking. The configuration file contains encrypted network share credentials and destination paths for data exfiltration. It specifically references the thumbcache_605a.db file created by ThumbcacheService as the file to be exfiltrated, demonstrating the integrated nature of the attack chain.
What distinguishes this threat actor’s approach is the deliberate integration between different components of their toolset. The chain from ThumbcacheService to TmcLoader/TmcPayload demonstrates sophisticated operational planning:
thumbcache_605a.db database file.thumbcache_605a.db.This integration shows that the threat actor has carefully orchestrated their tools to work together seamlessly, ensuring that data collected by one component is available for exfiltration by another component.
The malware operators leverage legitimate hosting providers, including Alibaba Cloud and UCLOUD HK, for their command-and-control infrastructure. The use of legitimate hosting platforms demonstrates operational security awareness, making detection more challenging.
The technical similarities between GoSerpent and the newer Stowaway tools strongly suggest the threat actor’s deep familiarity with network proxy technologies. The consistent use of legitimate domain names as secret keys, with GoSerpent employing www.microsoft.com and www.spacex.com and Stowaway utilizing github.code, indicates a standardized operational methodology.
While the exact attribution of the GoSerpent campaign remains uncertain, there are indications of a potential link to the TetrisPhantom threat actor. The similarities in victim targeting, technical capabilities, and operational methodologies suggest a possible connection. However, further investigation is necessary to confirm this association.
The GoSerpent campaign represents a sophisticated and evolving threat to government and diplomatic entities in Southeast Asia. The threat actor’s use of customized tools, such as the GoSerpent backdoor, Stowaway, and TmcLoader, demonstrates a high degree of technical expertise and operational planning. The integration of these tools to collect and exfiltrate sensitive data highlights the actor’s focus on long-term access and intelligence gathering. As the threat landscape continues to shift, it is essential for organizations to remain vigilant and implement robust security measures to detect and prevent such attacks. By understanding the tactics, techniques, and procedures (TTPs) employed by this threat actor, defenders can better prepare themselves to counter similar threats in the future.
GoSerpent
EBFFD5A76AAA690BCDB922F82E0BACC5
DC506FF7BB72735444FB3703A6BEE6D8
McMx
D6E86BF8A90E9B632ADD5FA495F97FBC
ThumbcacheService
CB6C4C70A3B171FA3404B8E1A3382116
64E9D1950E42BC98486DFD9919463D1C
Stowaway
CBBB6D483737EA3566726E51752DFF40
7F223EE0716CE2AD56F55D3744419449
19F8BEFCB035F52BF70094E6B4F5779A
846EF7C1C7323849B2A778C5E4CDA162
TmcLoader
D08A059E8B815E3B891505BC8777FC28
93A1569D5D5AB2C4761FEDF84F83709E
152.32.160[.]239
8.220.194[.]108
8.220.214[.]132
8.220.209[.]155
8.220.193[.]189
101.36.104[.]87
144.48.6[.]46
103.138.13[.]30
47.80.22[.]58
152.32.222[.]113
43.106.30[.]226
In January 2026, we identified multiple attacks involving unknown malware that captures the contents of cryptocurrency wallet windows. During the investigation, we reconstructed the complete infection chain, which consisted of four tightly linked stages initiated by the execution of the previously described malicious PowerShell script TookPS. However, this campaign differs from previous activity in that it uses a new framework to deliver all malicious modules and orchestrate them via an SSH tunnel. In total, the framework includes more than 20 malicious payloads and implants, covering a wide variety of functions. At the time of writing, the threat remains active.
Kaspersky’s products detect this threat as Trojan-Downloader.Win32.TookPS.*, Trojan.Win64.BypassUAC.*, Trojan-Banker.Script.Agent.gen, Trojan.Win32.Dllhijack.*, Backdoor.Win32.TeviRat.*, Trojan-PSW.Win64.Stealer.*, Trojan-Spy.Win64.Keylogger.*, Trojan-Spy.Win64.Agent.*, Trojan.Win64.Agent.*.
TookPS is a downloader used for retrieving malicious commands and scripts from attacker-controlled servers to further propagate attacks. The first campaign using TookPS was discovered in March 2025. At that time, malicious scripts delivered a Python‑based infostealer along with a script that installed and configured an SSH tunnel on the victim’s machine. The next wave appeared in April 2025: the payload was changed, and TookPS was used to deliver the TeviRAT malware with the same SSH installer.
Then at the end of April 2025, TookPS underwent minor changes, yet its attack chain was completely redesigned. Unlike previous incidents, in this case, TookPS was used solely for the initial infection, with an automated SSH bot responsible for payload delivery. This new malicious campaign has multiple stages that cover the full attack lifecycle, from initial infection to persistence and data exfiltration. Among various malware strains, at one of the stages, the TeviRAT backdoor is delivered to the compromised host, ultimately fetching another version of a TookPS script.
We dubbed this updated TookPS campaign “OkoBot”.
Original OkoBot infection chain
We will break down this chain in greater detail later in the article. However, this is not the only version of OkoBot we were able to find. Already in March 2026, we discovered a new phase in the development of the framework, with Volume2 now being installed directly using TookPS. The HDUtil launcher → extl injector → Rilide chain was found to be abandoned in this newer version since it was replaced in full by the identical ext_daemon Volume2 plugin. TeviRAT was also removed, most likely because its functions were covered by the new plugins dispatcher.
New OkoBot infection chain
The initial infection is primarily delivered through two vectors: a ClickFix attack, and malware distributed through GitHub that masquerades as legitimate software. One such example is the fake SQL Server Management Studio (SSMS) package distributed through GitHub. In fact, it is actually the legitimate Audacity — a popular audio editor — compiled with a malicious implant embedded in one of its libraries. Because the repository was indexed by most search engines and appeared at the top of the results for the query SSMS, the malware looked legitimate and quickly earned users’ trust.
Malicious application distribution report
This repository was created at the end of March 2025 and existed until June of that year. It consisted of a single file, README.md, which provided a fake SSMS installation guide written in an official style and likely derived from excerpts of Microsoft’s documentation. However, the download link for the program, located at the beginning of the guide, pointed to the latest release in the same repository.
Both infection vectors trigger the execution of the malicious script TookPS, which installs SSH on the victim’s system, establishes a connection to the attacker-controlled SSH server and subsequently forwards the SSH daemon port. Following a delay, an automated SSH bot connects to the forwarded port.
The automated SSH bot collects system information such as usernames, antivirus software installed, the IP address, and OS version. It harvests cryptocurrency wallet files, browser cookies, profiles, and other credentials through an SSH tunnel. For subsequent delivery of malicious modules, it disables Windows Defender notifications via a registry modification. Moreover, it gains access to the graphical session on the victim’s system using the following sequence:
termsrv.dll with a patched one to permit multiple concurrent RDP sessionsApple Sync to maintain a reverse SSH tunnel that forwards the local RDP port every hourAfter that, the SSH bot begins retrieving malicious modules over SFTP.
One of the deployed modules is HDUtil, an auxiliary utility protected with VMProtect and heavily obfuscated. This launcher is used by the SSH bot during an attack to deploy various malicious modules via the target command. Additionally, it implements three auxiliary commands that were not observed during the attacks we analyzed. Nevertheless, their presence and potential capabilities further demonstrate the high degree of integration among all components of the framework.
At startup, the launcher verifies its execution environment by checking the HWID in the contents of %PROGRAMDATA%\hwid.dat, a technique consistently employed throughout the framework. If the file is missing or contains invalid data, such as a non‑MD5 hash, the launcher terminates without performing any further actions. Otherwise, the specified commands are executed. For example, enumsessions provides a list of sessions along with detailed information, including the session type (Console, Services, RDP, and others), username, connection host, and domain. In turn, enumadapters returns the names of all graphics adapters present on the system.
Example output of HDUtil enumeration commands
The most important command of the launcher is target, which enables payload execution on the system. An optional nouac argument enables automatic UAC bypassing via Windows RPC and an auto-elevated msconfig.exe program, allowing the payload to run with elevated privileges stealthily. This technique has been known for a long time, discovered and described in 2019 by the Project Zero team, who provided a full report with a detailed technical description.
Below is the list of all HDUtil commands.
| Command | Description |
| target [nouac [user=<user>]] [noattach] <file> | Starts file and prints its output. If optional argument noattach passed, command to be executed in background. If optional argument nouac passed, automatic UAC bypass to be performed. If optional argument user passed, new process to be executed under , otherwise default local administrator to be chosen. |
| pcopy <file> <dir_src> <dir_dst> | Copies file <file> located in <dir_src> to <dir_dst>. Not used by SSH bot. |
| enumadapters | Prints names of graphical adapters on current system. Not used by SSH bot. |
| enumsessions | Prints all sessions on current system. Not used by SSH bot. |
The first malicious module delivered to the infected system via SFTP is executed using the previously described launcher with the command .\HDUtil.exe target extl.exe. It is a heavily obfuscated DLL injector protected with VMProtect. At startup, the module enters an infinite loop and uses the EnumWindows and IsWindowVisible API methods to enumerate the PIDs of active windows and retrieve the corresponding executable filenames. For processes associated with widely used Chromium‑based browsers, the module invokes a routine that injects a specialized implant.
The injector opens a process, allocates a memory region, and writes the payload directly into this region as unencrypted raw bytes. Then it resolves two exported implant functions, LdrInitMain and LdrCallMain, based on a pre-specified hash derived from a modified version of DJB2 hash function. The first function performs the final PE unpacking, including rebase operations and the initialization of the import and exception tables. The second function directly initiates malware execution.
Setting up protections on the regions and launching the implant
This loader installs malicious browser extensions and hides them from the user. It uses an internal engine that resolves the addresses of stripped functions by analyzing the byte patterns of their calls using YARA-style syntax. This approach enables the malicious code to access critical Chromium engine functions required for extension installation and management. This functionality is also implemented for other browsers with appropriate modifications. For example, in the case of Microsoft Edge, the corresponding DLL msedge.dll is hooked using the specific patterns.
List of the functions hooked by the malware
Using the obtained address of the BrowserProcess object, the loader traverses the inheritance hierarchy and subsequently resolves a pointer to the function responsible for registering observers of browser‑window creation, specifically ProfileManager::BrowserListObserver::OnBrowserAdded. With a specialized built‑in engine, they are hooked using the attacker’s own implementations while preserving the original function’s address.
The loader replaces the functions it finds with its own
When a new Chromium window is opened, a hooked function is invoked that silently installs extensions. This routine scans the user’s %APPDATA% directory, loads all .crx files (Chromium-based browsers extension format), and records them in the ext_table. The extensions are then installed in the browser.
During installation, the extension is unpacked into a non‑default extensions directory, Local Extension Settings, and its manifest is dynamically modified. An object named custom_args is added, containing the fields hwid (the identifier of the infected system) and browser (the name of the browser in which the extension is installed). Then, using previously resolved internal functions of chrome.dll, the extension is installed and all requested permissions are granted.
Extensions are unpacked into a non-default directory
All extensions loaded in this manner are added to a special array to be subsequently identified among regular extensions and to remain hidden from the user.
The remaining patched functions are used to hide the installed malicious extensions from the user. When invoked with registered extensions as parameters, they perform no operation and return a constant value. This enables the threat actor to suppress notifications related to the malicious nature of the extensions and to exclude them from the displayed list of installed extensions. As a result, the behavior of other extensions remains unaffected.
Stub for hiding malicious extensions
During the attack, the Rilide extension was installed on the victim’s system using the previously described loader. Rilide is a stealer targeting Chromium-based browsers that has been frequently used by Russian-speaking threat actors since April 2023. The malware is designed to steal sensitive user data, including login credentials, cookies, and financial information, with a specific emphasis on cryptocurrency theft.
The final module delivered via SFTP is an open-source utility called Volume2, which is executed with elevated privileges using the command .\HDUtil.exe target nouac noattach Volume2.exe. The executable was linked with the malicious protobuf.dll library. Although the library seems identical to the legitimate DLL, it has been modified to include a malicious exported function, ProtobufGetVer2. This function decrypts and initiates a malicious implant. The payload is encrypted using AES GCM, initialized with a static 256‑bit key and a 96‑bit nonce. The GCM authentication tag is omitted, resulting in the absence of integrity verification. Starting in March 2026, the name of protobuf.dll was changed to version.dll, although its contents remained a modified ProtoBuf library.
Decrypting implant using AES GCM and subsequent mapping
The loaded implant functions as a malicious plugin dispatcher. Upon initialization, it reads and verifies the HWID before establishing communication with the C2 server via the HTTP protocol. Each request follows a predefined binary format: a 2-byte numeric bot identifier encoded in little-endian format, followed by an AES CBC-encrypted JSON object. By default, the BotID is set to 0, and the key and IV consist of 32 and 16 bytes of 0xff, respectively. The implant polls the server every 20 seconds to retrieve new commands. The request contains client data encoded in Base64, and the server may respond with a command containing three mandatory fields: TaskIndex (the command number from the dispatcher), TaskID (a unique task identifier), and HWID (the client identifier). The dispatcher supports four built-in commands:
| Task index | Action |
| 1 | Reconfigure client: update session keys, assign ID, switch to another C2 |
| 2 | Load DLL implant into memory and run its entry point |
| 3 | Load plugin into process and register tasks with RegisterPlugin function |
| 4 | Restart dispatcher as new process |
| x | If the task number is none of the above, search for it among the registered plugins |
Each plugin is required to export two functions: RegisterPlugin and PluginDispatch. These functions are used to manage and configure plugins. The RegisterPlugin function registers the plugin’s tasks with the dispatcher, whereas the PluginDispatch function is invoked when the plugin is called. Both these functions, as well as other external API functions, are located within the base libraries using one algorithm. This algorithm iterates through the export table and uses a specialized callback that calculates the MurmurHash3 hash and compares it against the target value to identify the appropriate function.
Resolving a plugin initialization function
During the analysis, we were able to discover five plugins that implement functions under their unique task identifiers.
We identified four malicious implants that are delivered to the system via the process injector plugin.
The malware is functionally identical to the browser extensions loader (extl.exe) described above, but less obfuscated and not protected with VMProtect.
Similarly to extl.exe, this malware monitors the list of active processes in the system and injects an implant into Trezor Suite, Ledger Wallet, and Ledger Live processes. The implant is malware that collects seed phrases of Ledger and Trezor cryptocurrency wallets. Initially, it verifies the HWID, and if it fails, it terminates immediately. Then, based on the value of BaseDllName, the malware determines the process context and uses the corresponding implementation for either Trezor or Ledger. It then utilizes the previously described technique to hook the internal Electron framework functions.
List of functions hooked by the malware
Then the malware communicates with the C2 (moonsand[.]store) over HTTPS, sending a Base64-encoded JSON request containing the fields Pid, HWID, and Build. In response, it receives a JSON payload containing the Wait flag. If this flag is set to true, the malware initiates periodic USB device scans filtered by VID and PID (Vendor and Product ID). Upon detecting a connected Trezor or Ledger hardware wallet, it invokes the hooked functions to display a hard‑coded phishing page designed for seed phrase recovery, with a distinct layout used for each identified wallet. If the Wait flag is set to false, the phishing page is displayed immediately.
When the seed phrase is entered and validated, the JavaScript code of the page outputs the phrase to the console prefixed with @:app:print. This prefix helps identify the malware messages in the hooked function mal_LogConsoleMessage.
Phishing pages for seed phrase recovery
The obtained seed phrase is subsequently sent to the C2 server within a JSON payload containing fields such as App (ledger or trezor), Build, DeviceName, DeviceHardwareId, and SeedData. Furthermore, an identical JSON, encrypted with the RC4 algorithm using the HWID as the key, is saved in a temporary directory under the filename sh_<ts>.json, where <ts> is the file creation timestamp.
This module is a keylogger that, in addition to recording user input, performs three malicious activities:
CF_HDROP for files dragged between windows, CF_DIB for copied bitmap images, and CF_UNICODETEXT for Unicode text. Each format is handled appropriately, and all copy events are logged under the Clipboard section. Text data is written directly to the log, while copied files are recorded by their file paths. Images are saved as JPG files following the naming pattern bf_YYYY-MM-DD hh_mm_ss.jpg, and the path to the saved image is added to the log.sc_YYYY-MM-DD hh_mm_ss.jpg. A corresponding message is recorded in the log under the Screenshot section, including the path to the screenshot.Thus, the keylogger creates three types of different file artifacts, which are placed in a temporary directory. Below is an example of a log file generated by the keylogger.
Example of the keylogger log file
This module, which we dubbed OkoSpyware, captures both keystrokes and the video stream of the target application’s window. It first compiles a list of over 100 executable names, including cryptocurrency wallet applications (such as Exodus or Litecoin QT), password managers (such as KeePassXC or 1Password), and other widely used applications, to identify which processes should be monitored among all active system processes. For each identified process, the module uses a bundled FFmpeg instance to capture an MP4 video of the window while concurrently logging keystrokes within that window. The resulting video file is saved in %TEMP% as media_<ts> (where <ts> is the recording’s start timestamp). In the same folder, a JSON file named oko_<ts>.json is created, containing metadata about the captured stream, such as the process name, intercepted input, the stream’s MD5 hash, and additional details.
Example of an OkoSpyware metadata file
The malware also monitors the state of browsers, and when the window title matches a specified regular expression — for instance, a MetaMask or Tonkeeper wallet extension page — it performs video recording and input logging, adding the window title value to the corresponding field in the JSON metadata file.
The TookPS script launched via a scheduled task receives a PowerShell exfiltration script as its payload from the C2. All files created by the MC Keylogger and OkoSpyware are sent to the C2 server to the endpoint ir-post.php. After that, the files are deleted from the victim’s system and a command history file, ConsoleHost_history.txt, is cleared.
Sequential exfiltration of artifacts from the temporary directory
At the time of writing, we have detected hundreds of victims of the OkoBot campaign in more than 25 countries, with the largest proportion of attacked end users found in Brazil, Vietnam, Canada, Mexico, and Türkiye.
Distribution of users attacked by OkoBot by country, April 2025–June 2026 (download)
At the time of writing, we can’t attribute this malicious campaign to any known crimeware actor. However, during the analysis, we observed that the servers hosting the PowerShell scripts used in the initial infection stage implement server-side geoblocking. When attempting to retrieve the malicious script using an IP from Russia or CIS countries, the server returns an empty response. This technique is very popular among Russian-speaking threat actors.
It was previously mentioned that the campaign uses the malicious Rilide extension, an infostealer that is actively spreading on Russian-speaking, invitation-only cybercrime forums. Additionally, the source code of the SeedHunter phishing pages includes comments in Russian.
The framework described here has numerous modules — mostly written in C and C++ — that are obfuscated and use a variety of packing techniques. Across all stages, specific patterns and techniques can be identified that are borrowed and used in other modules, which allows us to conclude that there is a close interconnectedness among all stages, forming a full‑fledged high‑level framework. Overall, these modules enable a wide range of functions, such as collecting local files, executing remote commands, downloading arbitrary browser extensions, and stealing crypto wallets.
The OkoBot campaign has been ongoing for over a year, and it remains active at the time of publication. Moreover, it is adapting, which indicates that this framework is being maintained and distribution campaigns continue.
Additional information about this threat, with a comprehensive IoC list and decryption scripts, is available to customers of the Kaspersky Threat Intelligence Reporting service. Contact: intelreports@kaspersky.com.
B07D451EE65A1580F20A784C8F0E7A46 # protobuf.dll
187A1F68AE786E53D3831166DC84E6D2 # protobuf.dll
D84E8DC509308523E0209D3CD3544619 # protobuf.dll
83E6B8FCB92A0B13E109301F8FF649CF # version.dll
7306885BB4C98F2A9F056104CF092BC9 # PowerShell wrapper
B4C2E16CDB513BE4DC798F88E2527334 # CMD wrapper
2157D2429124AD28DB7A26F2477CB985 # Environment enumerator
77CECF5E2A622AE07D8AE9913457AB57 # Dropper
E0C3BC27A65750E740C4F1719E531C7D # Process injector
3D2B43F91F65BFBF36A9C71B6B418876 # ext_daemon.exe
70FEF9FD6E351F4D53CFEEE8DCDFCD99 # seedhunter_x64.exe
ACD31C9941B6C1CABD4E45E6877B9038 # keylog_x64.dll
DD52F5108A176C62AD807C327734AD12 # oko.dll
AC93A821617AEA1F56D4BC0BEF4AF327 # HDUtil.exe
11DBC8A2BEA04B15F8F68F3F01E8FAF9 # extl.exe
%USERPROFILE%\.ssh\go.bat
%PROGRAMDATA%\HDVideo\HDUtil.exe
%PROGRAMDATA%\hwid.dat
%PROGRAMDATA%\oko_ver
%TEMP%\extl.exe
%APPDATA%\hwid.dat
2baserec2[.]guru # TookPS
recavb22[.]online # TookPS
kbeautyreviews[.]com # TookPS
coffeesaloon[.]online # TookPS
104.243.43[.]16 # SSH bot
104.243.32[.]213 # SSH bot
62.210.188[.]209 # SSH bot
livewallpapers[.]online # Volume2 C2
thatwascringe[.]com # Volume2 C2
moonsand[.]store # SeedHunter C2
In January 2026, we identified multiple attacks involving unknown malware that captures the contents of cryptocurrency wallet windows. During the investigation, we reconstructed the complete infection chain, which consisted of four tightly linked stages initiated by the execution of the previously described malicious PowerShell script TookPS. However, this campaign differs from previous activity in that it uses a new framework to deliver all malicious modules and orchestrate them via an SSH tunnel. In total, the framework includes more than 20 malicious payloads and implants, covering a wide variety of functions. At the time of writing, the threat remains active.
Kaspersky’s products detect this threat as Trojan-Downloader.Win32.TookPS.*, Trojan.Win64.BypassUAC.*, Trojan-Banker.Script.Agent.gen, Trojan.Win32.Dllhijack.*, Backdoor.Win32.TeviRat.*, Trojan-PSW.Win64.Stealer.*, Trojan-Spy.Win64.Keylogger.*, Trojan-Spy.Win64.Agent.*, Trojan.Win64.Agent.*.
TookPS is a downloader used for retrieving malicious commands and scripts from attacker-controlled servers to further propagate attacks. The first campaign using TookPS was discovered in March 2025. At that time, malicious scripts delivered a Python‑based infostealer along with a script that installed and configured an SSH tunnel on the victim’s machine. The next wave appeared in April 2025: the payload was changed, and TookPS was used to deliver the TeviRAT malware with the same SSH installer.
Then at the end of April 2025, TookPS underwent minor changes, yet its attack chain was completely redesigned. Unlike previous incidents, in this case, TookPS was used solely for the initial infection, with an automated SSH bot responsible for payload delivery. This new malicious campaign has multiple stages that cover the full attack lifecycle, from initial infection to persistence and data exfiltration. Among various malware strains, at one of the stages, the TeviRAT backdoor is delivered to the compromised host, ultimately fetching another version of a TookPS script.
We dubbed this updated TookPS campaign “OkoBot”.
Original OkoBot infection chain
We will break down this chain in greater detail later in the article. However, this is not the only version of OkoBot we were able to find. Already in March 2026, we discovered a new phase in the development of the framework, with Volume2 now being installed directly using TookPS. The HDUtil launcher → extl injector → Rilide chain was found to be abandoned in this newer version since it was replaced in full by the identical ext_daemon Volume2 plugin. TeviRAT was also removed, most likely because its functions were covered by the new plugins dispatcher.
New OkoBot infection chain
The initial infection is primarily delivered through two vectors: a ClickFix attack, and malware distributed through GitHub that masquerades as legitimate software. One such example is the fake SQL Server Management Studio (SSMS) package distributed through GitHub. In fact, it is actually the legitimate Audacity — a popular audio editor — compiled with a malicious implant embedded in one of its libraries. Because the repository was indexed by most search engines and appeared at the top of the results for the query SSMS, the malware looked legitimate and quickly earned users’ trust.
Malicious application distribution report
This repository was created at the end of March 2025 and existed until June of that year. It consisted of a single file, README.md, which provided a fake SSMS installation guide written in an official style and likely derived from excerpts of Microsoft’s documentation. However, the download link for the program, located at the beginning of the guide, pointed to the latest release in the same repository.
Both infection vectors trigger the execution of the malicious script TookPS, which installs SSH on the victim’s system, establishes a connection to the attacker-controlled SSH server and subsequently forwards the SSH daemon port. Following a delay, an automated SSH bot connects to the forwarded port.
The automated SSH bot collects system information such as usernames, antivirus software installed, the IP address, and OS version. It harvests cryptocurrency wallet files, browser cookies, profiles, and other credentials through an SSH tunnel. For subsequent delivery of malicious modules, it disables Windows Defender notifications via a registry modification. Moreover, it gains access to the graphical session on the victim’s system using the following sequence:
termsrv.dll with a patched one to permit multiple concurrent RDP sessionsApple Sync to maintain a reverse SSH tunnel that forwards the local RDP port every hourAfter that, the SSH bot begins retrieving malicious modules over SFTP.
One of the deployed modules is HDUtil, an auxiliary utility protected with VMProtect and heavily obfuscated. This launcher is used by the SSH bot during an attack to deploy various malicious modules via the target command. Additionally, it implements three auxiliary commands that were not observed during the attacks we analyzed. Nevertheless, their presence and potential capabilities further demonstrate the high degree of integration among all components of the framework.
At startup, the launcher verifies its execution environment by checking the HWID in the contents of %PROGRAMDATA%\hwid.dat, a technique consistently employed throughout the framework. If the file is missing or contains invalid data, such as a non‑MD5 hash, the launcher terminates without performing any further actions. Otherwise, the specified commands are executed. For example, enumsessions provides a list of sessions along with detailed information, including the session type (Console, Services, RDP, and others), username, connection host, and domain. In turn, enumadapters returns the names of all graphics adapters present on the system.
Example output of HDUtil enumeration commands
The most important command of the launcher is target, which enables payload execution on the system. An optional nouac argument enables automatic UAC bypassing via Windows RPC and an auto-elevated msconfig.exe program, allowing the payload to run with elevated privileges stealthily. This technique has been known for a long time, discovered and described in 2019 by the Project Zero team, who provided a full report with a detailed technical description.
Below is the list of all HDUtil commands.
| Command | Description |
| target [nouac [user=<user>]] [noattach] <file> | Starts file and prints its output. If optional argument noattach passed, command to be executed in background. If optional argument nouac passed, automatic UAC bypass to be performed. If optional argument user passed, new process to be executed under , otherwise default local administrator to be chosen. |
| pcopy <file> <dir_src> <dir_dst> | Copies file <file> located in <dir_src> to <dir_dst>. Not used by SSH bot. |
| enumadapters | Prints names of graphical adapters on current system. Not used by SSH bot. |
| enumsessions | Prints all sessions on current system. Not used by SSH bot. |
The first malicious module delivered to the infected system via SFTP is executed using the previously described launcher with the command .\HDUtil.exe target extl.exe. It is a heavily obfuscated DLL injector protected with VMProtect. At startup, the module enters an infinite loop and uses the EnumWindows and IsWindowVisible API methods to enumerate the PIDs of active windows and retrieve the corresponding executable filenames. For processes associated with widely used Chromium‑based browsers, the module invokes a routine that injects a specialized implant.
The injector opens a process, allocates a memory region, and writes the payload directly into this region as unencrypted raw bytes. Then it resolves two exported implant functions, LdrInitMain and LdrCallMain, based on a pre-specified hash derived from a modified version of DJB2 hash function. The first function performs the final PE unpacking, including rebase operations and the initialization of the import and exception tables. The second function directly initiates malware execution.
Setting up protections on the regions and launching the implant
This loader installs malicious browser extensions and hides them from the user. It uses an internal engine that resolves the addresses of stripped functions by analyzing the byte patterns of their calls using YARA-style syntax. This approach enables the malicious code to access critical Chromium engine functions required for extension installation and management. This functionality is also implemented for other browsers with appropriate modifications. For example, in the case of Microsoft Edge, the corresponding DLL msedge.dll is hooked using the specific patterns.
List of the functions hooked by the malware
Using the obtained address of the BrowserProcess object, the loader traverses the inheritance hierarchy and subsequently resolves a pointer to the function responsible for registering observers of browser‑window creation, specifically ProfileManager::BrowserListObserver::OnBrowserAdded. With a specialized built‑in engine, they are hooked using the attacker’s own implementations while preserving the original function’s address.
The loader replaces the functions it finds with its own
When a new Chromium window is opened, a hooked function is invoked that silently installs extensions. This routine scans the user’s %APPDATA% directory, loads all .crx files (Chromium-based browsers extension format), and records them in the ext_table. The extensions are then installed in the browser.
During installation, the extension is unpacked into a non‑default extensions directory, Local Extension Settings, and its manifest is dynamically modified. An object named custom_args is added, containing the fields hwid (the identifier of the infected system) and browser (the name of the browser in which the extension is installed). Then, using previously resolved internal functions of chrome.dll, the extension is installed and all requested permissions are granted.
Extensions are unpacked into a non-default directory
All extensions loaded in this manner are added to a special array to be subsequently identified among regular extensions and to remain hidden from the user.
The remaining patched functions are used to hide the installed malicious extensions from the user. When invoked with registered extensions as parameters, they perform no operation and return a constant value. This enables the threat actor to suppress notifications related to the malicious nature of the extensions and to exclude them from the displayed list of installed extensions. As a result, the behavior of other extensions remains unaffected.
Stub for hiding malicious extensions
During the attack, the Rilide extension was installed on the victim’s system using the previously described loader. Rilide is a stealer targeting Chromium-based browsers that has been frequently used by Russian-speaking threat actors since April 2023. The malware is designed to steal sensitive user data, including login credentials, cookies, and financial information, with a specific emphasis on cryptocurrency theft.
The final module delivered via SFTP is an open-source utility called Volume2, which is executed with elevated privileges using the command .\HDUtil.exe target nouac noattach Volume2.exe. The executable was linked with the malicious protobuf.dll library. Although the library seems identical to the legitimate DLL, it has been modified to include a malicious exported function, ProtobufGetVer2. This function decrypts and initiates a malicious implant. The payload is encrypted using AES GCM, initialized with a static 256‑bit key and a 96‑bit nonce. The GCM authentication tag is omitted, resulting in the absence of integrity verification. Starting in March 2026, the name of protobuf.dll was changed to version.dll, although its contents remained a modified ProtoBuf library.
Decrypting implant using AES GCM and subsequent mapping
The loaded implant functions as a malicious plugin dispatcher. Upon initialization, it reads and verifies the HWID before establishing communication with the C2 server via the HTTP protocol. Each request follows a predefined binary format: a 2-byte numeric bot identifier encoded in little-endian format, followed by an AES CBC-encrypted JSON object. By default, the BotID is set to 0, and the key and IV consist of 32 and 16 bytes of 0xff, respectively. The implant polls the server every 20 seconds to retrieve new commands. The request contains client data encoded in Base64, and the server may respond with a command containing three mandatory fields: TaskIndex (the command number from the dispatcher), TaskID (a unique task identifier), and HWID (the client identifier). The dispatcher supports four built-in commands:
| Task index | Action |
| 1 | Reconfigure client: update session keys, assign ID, switch to another C2 |
| 2 | Load DLL implant into memory and run its entry point |
| 3 | Load plugin into process and register tasks with RegisterPlugin function |
| 4 | Restart dispatcher as new process |
| x | If the task number is none of the above, search for it among the registered plugins |
Each plugin is required to export two functions: RegisterPlugin and PluginDispatch. These functions are used to manage and configure plugins. The RegisterPlugin function registers the plugin’s tasks with the dispatcher, whereas the PluginDispatch function is invoked when the plugin is called. Both these functions, as well as other external API functions, are located within the base libraries using one algorithm. This algorithm iterates through the export table and uses a specialized callback that calculates the MurmurHash3 hash and compares it against the target value to identify the appropriate function.
Resolving a plugin initialization function
During the analysis, we were able to discover five plugins that implement functions under their unique task identifiers.
We identified four malicious implants that are delivered to the system via the process injector plugin.
The malware is functionally identical to the browser extensions loader (extl.exe) described above, but less obfuscated and not protected with VMProtect.
Similarly to extl.exe, this malware monitors the list of active processes in the system and injects an implant into Trezor Suite, Ledger Wallet, and Ledger Live processes. The implant is malware that collects seed phrases of Ledger and Trezor cryptocurrency wallets. Initially, it verifies the HWID, and if it fails, it terminates immediately. Then, based on the value of BaseDllName, the malware determines the process context and uses the corresponding implementation for either Trezor or Ledger. It then utilizes the previously described technique to hook the internal Electron framework functions.
List of functions hooked by the malware
Then the malware communicates with the C2 (moonsand[.]store) over HTTPS, sending a Base64-encoded JSON request containing the fields Pid, HWID, and Build. In response, it receives a JSON payload containing the Wait flag. If this flag is set to true, the malware initiates periodic USB device scans filtered by VID and PID (Vendor and Product ID). Upon detecting a connected Trezor or Ledger hardware wallet, it invokes the hooked functions to display a hard‑coded phishing page designed for seed phrase recovery, with a distinct layout used for each identified wallet. If the Wait flag is set to false, the phishing page is displayed immediately.
When the seed phrase is entered and validated, the JavaScript code of the page outputs the phrase to the console prefixed with @:app:print. This prefix helps identify the malware messages in the hooked function mal_LogConsoleMessage.
Phishing pages for seed phrase recovery
The obtained seed phrase is subsequently sent to the C2 server within a JSON payload containing fields such as App (ledger or trezor), Build, DeviceName, DeviceHardwareId, and SeedData. Furthermore, an identical JSON, encrypted with the RC4 algorithm using the HWID as the key, is saved in a temporary directory under the filename sh_<ts>.json, where <ts> is the file creation timestamp.
This module is a keylogger that, in addition to recording user input, performs three malicious activities:
CF_HDROP for files dragged between windows, CF_DIB for copied bitmap images, and CF_UNICODETEXT for Unicode text. Each format is handled appropriately, and all copy events are logged under the Clipboard section. Text data is written directly to the log, while copied files are recorded by their file paths. Images are saved as JPG files following the naming pattern bf_YYYY-MM-DD hh_mm_ss.jpg, and the path to the saved image is added to the log.sc_YYYY-MM-DD hh_mm_ss.jpg. A corresponding message is recorded in the log under the Screenshot section, including the path to the screenshot.Thus, the keylogger creates three types of different file artifacts, which are placed in a temporary directory. Below is an example of a log file generated by the keylogger.
Example of the keylogger log file
This module, which we dubbed OkoSpyware, captures both keystrokes and the video stream of the target application’s window. It first compiles a list of over 100 executable names, including cryptocurrency wallet applications (such as Exodus or Litecoin QT), password managers (such as KeePassXC or 1Password), and other widely used applications, to identify which processes should be monitored among all active system processes. For each identified process, the module uses a bundled FFmpeg instance to capture an MP4 video of the window while concurrently logging keystrokes within that window. The resulting video file is saved in %TEMP% as media_<ts> (where <ts> is the recording’s start timestamp). In the same folder, a JSON file named oko_<ts>.json is created, containing metadata about the captured stream, such as the process name, intercepted input, the stream’s MD5 hash, and additional details.
Example of an OkoSpyware metadata file
The malware also monitors the state of browsers, and when the window title matches a specified regular expression — for instance, a MetaMask or Tonkeeper wallet extension page — it performs video recording and input logging, adding the window title value to the corresponding field in the JSON metadata file.
The TookPS script launched via a scheduled task receives a PowerShell exfiltration script as its payload from the C2. All files created by the MC Keylogger and OkoSpyware are sent to the C2 server to the endpoint ir-post.php. After that, the files are deleted from the victim’s system and a command history file, ConsoleHost_history.txt, is cleared.
Sequential exfiltration of artifacts from the temporary directory
At the time of writing, we have detected hundreds of victims of the OkoBot campaign in more than 25 countries, with the largest proportion of attacked end users found in Brazil, Vietnam, Canada, Mexico, and Türkiye.
Distribution of users attacked by OkoBot by country, April 2025–June 2026 (download)
At the time of writing, we can’t attribute this malicious campaign to any known crimeware actor. However, during the analysis, we observed that the servers hosting the PowerShell scripts used in the initial infection stage implement server-side geoblocking. When attempting to retrieve the malicious script using an IP from Russia or CIS countries, the server returns an empty response. This technique is very popular among Russian-speaking threat actors.
It was previously mentioned that the campaign uses the malicious Rilide extension, an infostealer that is actively spreading on Russian-speaking, invitation-only cybercrime forums. Additionally, the source code of the SeedHunter phishing pages includes comments in Russian.
The framework described here has numerous modules — mostly written in C and C++ — that are obfuscated and use a variety of packing techniques. Across all stages, specific patterns and techniques can be identified that are borrowed and used in other modules, which allows us to conclude that there is a close interconnectedness among all stages, forming a full‑fledged high‑level framework. Overall, these modules enable a wide range of functions, such as collecting local files, executing remote commands, downloading arbitrary browser extensions, and stealing crypto wallets.
The OkoBot campaign has been ongoing for over a year, and it remains active at the time of publication. Moreover, it is adapting, which indicates that this framework is being maintained and distribution campaigns continue.
Additional information about this threat, with a comprehensive IoC list and decryption scripts, is available to customers of the Kaspersky Threat Intelligence Reporting service. Contact: intelreports@kaspersky.com.
B07D451EE65A1580F20A784C8F0E7A46 # protobuf.dll
187A1F68AE786E53D3831166DC84E6D2 # protobuf.dll
D84E8DC509308523E0209D3CD3544619 # protobuf.dll
83E6B8FCB92A0B13E109301F8FF649CF # version.dll
7306885BB4C98F2A9F056104CF092BC9 # PowerShell wrapper
B4C2E16CDB513BE4DC798F88E2527334 # CMD wrapper
2157D2429124AD28DB7A26F2477CB985 # Environment enumerator
77CECF5E2A622AE07D8AE9913457AB57 # Dropper
E0C3BC27A65750E740C4F1719E531C7D # Process injector
3D2B43F91F65BFBF36A9C71B6B418876 # ext_daemon.exe
70FEF9FD6E351F4D53CFEEE8DCDFCD99 # seedhunter_x64.exe
ACD31C9941B6C1CABD4E45E6877B9038 # keylog_x64.dll
DD52F5108A176C62AD807C327734AD12 # oko.dll
AC93A821617AEA1F56D4BC0BEF4AF327 # HDUtil.exe
11DBC8A2BEA04B15F8F68F3F01E8FAF9 # extl.exe
%USERPROFILE%\.ssh\go.bat
%PROGRAMDATA%\HDVideo\HDUtil.exe
%PROGRAMDATA%\hwid.dat
%PROGRAMDATA%\oko_ver
%TEMP%\extl.exe
%APPDATA%\hwid.dat
2baserec2[.]guru # TookPS
recavb22[.]online # TookPS
kbeautyreviews[.]com # TookPS
coffeesaloon[.]online # TookPS
104.243.43[.]16 # SSH bot
104.243.32[.]213 # SSH bot
62.210.188[.]209 # SSH bot
livewallpapers[.]online # Volume2 C2
thatwascringe[.]com # Volume2 C2
moonsand[.]store # SeedHunter C2
During our recent threat hunting activities, we found EtherRAT malware being distributed by a website with a strange homepage. This homepage allowed us to discover a vast malicious infrastructure distributing malware, malicious documents, remote desktop software, and phishing pages.
EtherRAT is a RAT developed in Node.js which allows an attacker to gain complete control over the machine and execute arbitrary code returned by the Command and Control (C2) server. The malware uses the Etherium blockchain to obtain the C2 server, hence the “Ether” part of the name. EtherRAT is typically distributed via MSI, PowerShell, or JavaScript scripts.
While threat hunting, we found an open directory that was distributing MSI installers and PowerShell scripts, which ultimately distributed EtherRAT. In the analyzed cases, the PowerShell scripts and MSI installers were distributed from a “/install” folder. The versions have a progressive number, ranging from v1 to v10.
The returned home page caught our attention and prompted us to further explore the campaign.
Analyzing domains and associated IPs with the EtherRAT distribution, we detected other similar home pages with a hacking-style theme. They appeared to belong to a larger distribution chain, which also distributes phishing, remote control software, and other malware. These websites usually have several folders with malware and phishing related content, and what is displayed depends on the specific infection chain.
Different websites that resolve to the same IP addresses have previously returned pages related to fake companies or default templates. The use of these new pages could therefore be a method to make detection more difficult for automated scanners or researchers. Here are some of the home pages we found:
EtherRAT is an interesting RAT, as it has few lines of code and allows the execution of arbitrary code returned by the C2 server. Furthermore, using the Ethereum blockchain to obtain the C2 server makes it more resilient to infrastructure takedowns.
The detected websites usually distribute an MSI or PowerShell script with the version name, such as v1.msi, v2.ps1, and so on.
The MSI file “v9.msi” contains three components:
| MSI Filename | Description |
| KmPuGimn.cmd | BAT launcher |
| cDQMlQAru0.xml | First Jscript loader |
| MRaQCipBIZeiZNx.log | Encrypted EtherRAT |
When the MSI is executed, the “KmPuGimn.cmd” file is started:
conhost --headless cmd /c "KmPuGimn.cmd" This obfuscated BAT file performs different operations:
The executed “cDQMlQAru0.xml” is a loader that decrypts the embedded code with a XOR function and then executes it with “vm.compileFunction”.
decrypted[i] = (encrypted[i] - key[i % key.length] - i) & 0xFF The decrypted code:
The decryption algorithm is a custom stream-like decoding routing based on XOR, byte rotations and an accumulator:
for e in range(len(data)):
byte = data[e]
g = prev
prev = byte
byte = (byte - g) & 0xff
byte = byte ^ n[e % len(n)] ^ ((e >> 8) & 0xff)
byte = si[byte]
byte = (byte - k[e % len(k)]) & 0xff
result[e] = byte The final stage is to deploy EtherRAT. EtherRAT allows the attacker to:
The EtherRAT uses Ethereum’s “eth_call” JSON-RPC method to retrieve the active C2 URL from a smart contract on the Ethereum mainnet.
The blockchain parameters in this case are:
The contacted URLs to obtain the C2 server endpoint are:
Polling requests use randomized URL patterns based on some parameters defined in the code:
GET /api/<4-byte-hex>/<victim-uuid>/<4-byte-hex>.<ext>?<param>=<build-id>
X-Bot-Server: <c2_url> In the analyzed sample, the parameters are:
After startup, the RAT sends its own source code to the C2 server. The C2 responds with a newly obfuscated version of the script, which is written back to disk, making each execution generate a new file hash.
POST /api/[REOBF_PATH]/<victim-uuid>
Body: { "code": "<current_script_contents>", "build": "<build_id>" } After the EtherRAT execution, we observed different post-compromised cmd.exe activities to check the environment. For example:
The activities performed by the PowerShell loaders are very similar to the last stage of the JS script of the MSI installer:
We detected some variants of the PowerShell loader hosted on these websites; namely that the functions’ names and the decryption functions change in the analyzed PowerShell scripts.
When we analyzed the different websites with the “hacking-theme” pages, we found that in the past many had hosted multiple phishing pages in some specific paths. For example:
It seems that these domains and IPs are actually part of a much larger infrastructure that distributes malware, phishing, malicious documents, and remote software. It is possible that these infrastructures are shared by multiple threat actors who activate different URL endpoints based on the specific campaign.
Interestingly, the majority of the domains related to this malicious infrastructure in the past also returned an HTML page related to a “Bulletproof Infrastructure” service.
We found that these phishing campaigns typically start via emails with documents attached, such as PDF or Excel files. These documents ask the user to click a link to view another document. Below are two examples of the phishing documents attached to the emails:
These phishing pages typically ask the user to enter their email address, then continue the infection chain and distribute phishing or malware pages. Below are some of the phishing pages detected within the malicious infrastructure:
While tracking malicious websites, we found one with an open directory containing part of the phishing kit used in the campaigns.
The open directory contained several folders with code and pages related to the phishing campaigns.
Additionally, some domains were misconfigured and allowed the download of “cl.zip”, which contained the source code for the “URL Cloaker” pages.
82[.]165[.]65[.]244: malicious infrastructure
185[.]221[.]216[.]121: malicious infrastructure
43[.]163[.]233[.]166: malicious infrastructure
40[.]160[.]238[.]30: malicious infrastructure
159[.]89[.]227[.]204: malicious infrastructure
57[.]128[.]31[.]168: malicious infrastructure
ivorilla[.]cloud: EtherRAT distribution
mx[.]nrlwz[.]com: EtherRAT distribution
dn[.]eyqwj[.]com: EtherRAT distribution
bi[.]mkrjcsw[.]com: EtherRAT distribution
dorqen[.]casa: EtherRAT distribution
kelvra[.]club: EtherRAT distribution
cambioefectivo[.]com: EtherRAT C2
vabelles[.]com: EtherRAT C2
tranzed[.]org: EtherRAT C2
kibrisarazi[.]com: EtherRAT C2
aravisblog[.]com: EtherRAT C2
publicspeakingtip[.]org: EtherRAT C2
Stop threats before they can do any harm.
Malwarebytes Browser Guard blocks phishing pages and malicious sites automatically. Free, one click to install. Add it to your browser →
During our recent threat hunting activities, we found EtherRAT malware being distributed by a website with a strange homepage. This homepage allowed us to discover a vast malicious infrastructure distributing malware, malicious documents, remote desktop software, and phishing pages.
EtherRAT is a RAT developed in Node.js which allows an attacker to gain complete control over the machine and execute arbitrary code returned by the Command and Control (C2) server. The malware uses the Etherium blockchain to obtain the C2 server, hence the “Ether” part of the name. EtherRAT is typically distributed via MSI, PowerShell, or JavaScript scripts.
While threat hunting, we found an open directory that was distributing MSI installers and PowerShell scripts, which ultimately distributed EtherRAT. In the analyzed cases, the PowerShell scripts and MSI installers were distributed from a “/install” folder. The versions have a progressive number, ranging from v1 to v10.
The returned home page caught our attention and prompted us to further explore the campaign.
Analyzing domains and associated IPs with the EtherRAT distribution, we detected other similar home pages with a hacking-style theme. They appeared to belong to a larger distribution chain, which also distributes phishing, remote control software, and other malware. These websites usually have several folders with malware and phishing related content, and what is displayed depends on the specific infection chain.
Different websites that resolve to the same IP addresses have previously returned pages related to fake companies or default templates. The use of these new pages could therefore be a method to make detection more difficult for automated scanners or researchers. Here are some of the home pages we found:
EtherRAT is an interesting RAT, as it has few lines of code and allows the execution of arbitrary code returned by the C2 server. Furthermore, using the Ethereum blockchain to obtain the C2 server makes it more resilient to infrastructure takedowns.
The detected websites usually distribute an MSI or PowerShell script with the version name, such as v1.msi, v2.ps1, and so on.
The MSI file “v9.msi” contains three components:
| MSI Filename | Description |
| KmPuGimn.cmd | BAT launcher |
| cDQMlQAru0.xml | First Jscript loader |
| MRaQCipBIZeiZNx.log | Encrypted EtherRAT |
When the MSI is executed, the “KmPuGimn.cmd” file is started:
conhost --headless cmd /c "KmPuGimn.cmd" This obfuscated BAT file performs different operations:
The executed “cDQMlQAru0.xml” is a loader that decrypts the embedded code with a XOR function and then executes it with “vm.compileFunction”.
decrypted[i] = (encrypted[i] - key[i % key.length] - i) & 0xFF The decrypted code:
The decryption algorithm is a custom stream-like decoding routing based on XOR, byte rotations and an accumulator:
for e in range(len(data)):
byte = data[e]
g = prev
prev = byte
byte = (byte - g) & 0xff
byte = byte ^ n[e % len(n)] ^ ((e >> 8) & 0xff)
byte = si[byte]
byte = (byte - k[e % len(k)]) & 0xff
result[e] = byte The final stage is to deploy EtherRAT. EtherRAT allows the attacker to:
The EtherRAT uses Ethereum’s “eth_call” JSON-RPC method to retrieve the active C2 URL from a smart contract on the Ethereum mainnet.
The blockchain parameters in this case are:
The contacted URLs to obtain the C2 server endpoint are:
Polling requests use randomized URL patterns based on some parameters defined in the code:
GET /api/<4-byte-hex>/<victim-uuid>/<4-byte-hex>.<ext>?<param>=<build-id>
X-Bot-Server: <c2_url> In the analyzed sample, the parameters are:
After startup, the RAT sends its own source code to the C2 server. The C2 responds with a newly obfuscated version of the script, which is written back to disk, making each execution generate a new file hash.
POST /api/[REOBF_PATH]/<victim-uuid>
Body: { "code": "<current_script_contents>", "build": "<build_id>" } After the EtherRAT execution, we observed different post-compromised cmd.exe activities to check the environment. For example:
The activities performed by the PowerShell loaders are very similar to the last stage of the JS script of the MSI installer:
We detected some variants of the PowerShell loader hosted on these websites; namely that the functions’ names and the decryption functions change in the analyzed PowerShell scripts.
When we analyzed the different websites with the “hacking-theme” pages, we found that in the past many had hosted multiple phishing pages in some specific paths. For example:
It seems that these domains and IPs are actually part of a much larger infrastructure that distributes malware, phishing, malicious documents, and remote software. It is possible that these infrastructures are shared by multiple threat actors who activate different URL endpoints based on the specific campaign.
Interestingly, the majority of the domains related to this malicious infrastructure in the past also returned an HTML page related to a “Bulletproof Infrastructure” service.
We found that these phishing campaigns typically start via emails with documents attached, such as PDF or Excel files. These documents ask the user to click a link to view another document. Below are two examples of the phishing documents attached to the emails:
These phishing pages typically ask the user to enter their email address, then continue the infection chain and distribute phishing or malware pages. Below are some of the phishing pages detected within the malicious infrastructure:
While tracking malicious websites, we found one with an open directory containing part of the phishing kit used in the campaigns.
The open directory contained several folders with code and pages related to the phishing campaigns.
Additionally, some domains were misconfigured and allowed the download of “cl.zip”, which contained the source code for the “URL Cloaker” pages.
82[.]165[.]65[.]244: malicious infrastructure
185[.]221[.]216[.]121: malicious infrastructure
43[.]163[.]233[.]166: malicious infrastructure
40[.]160[.]238[.]30: malicious infrastructure
159[.]89[.]227[.]204: malicious infrastructure
57[.]128[.]31[.]168: malicious infrastructure
ivorilla[.]cloud: EtherRAT distribution
mx[.]nrlwz[.]com: EtherRAT distribution
dn[.]eyqwj[.]com: EtherRAT distribution
bi[.]mkrjcsw[.]com: EtherRAT distribution
dorqen[.]casa: EtherRAT distribution
kelvra[.]club: EtherRAT distribution
cambioefectivo[.]com: EtherRAT C2
vabelles[.]com: EtherRAT C2
tranzed[.]org: EtherRAT C2
kibrisarazi[.]com: EtherRAT C2
aravisblog[.]com: EtherRAT C2
publicspeakingtip[.]org: EtherRAT C2
Stop threats before they can do any harm.
Malwarebytes Browser Guard blocks phishing pages and malicious sites automatically. Free, one click to install. Add it to your browser →
In April 2026, we discovered a new campaign targeting users of hentai games. Attackers are embedding a remote access Trojan named Argamal into game installers. While concealing its presence, it can remotely control the computer and steal files and personal data.
Here’s how to avoid falling victim to this new Trojan — and how to safely and anonymously enjoy spicy content with (or without) anime girls.
Most of the infected games are distributed through adult game and torrent sites. In some cases, they are posted for download on file-sharing services and linked on gaming websites.
Example of a trojanized game hosted on the AniRena torrent tracker
Interestingly, instead of finding a dummy file inside the archive — as is often the case — the user gets the actual game built on popular engines like RenPy or RPG Maker. Infected pirated versions usually turn out to be scams: games fail to launch, folders are full of files with bizarre extensions, making it rather easy to put two and two together. Here, however, the user gets the actual gameplay they expected. Meanwhile, the Trojan lets itself in and keeps a completely low profile.
Example of a trojanized game hosted on the AniRena torrent tracker
Tucked right alongside the legitimate files in the archive is a DLL that the game relies on to run, but it’s been rigged: as soon as the user launches the game, the infected DLL automatically loads into memory. There are no outward signs of infection: neither an installer popping up in the background, nor a scary window or prompt asking you to disable your antivirus.
Argamal takes things real slow: instead of immediately rushing to steal files and passwords or throwing a digital rager on your computer, the Trojan first checks whether it’s running in a virtual machine or sandbox, and then goes into standby mode.
During this time, the malware writes hidden parameters to the system, conceals the paths to its DLLs, and delays its own execution. Three days later, the computer connects to GitHub, downloads an encrypted file, decrypts it, and turns it into a working Trojan module.
To ensure persistence, the attackers register the malware under the WindowsColorSystem Calibration Loader system task, a built-in Windows feature that triggers at every user logon to load monitor color profiles. Before shutting down, the malware deletes temporary files and covers its tracks to make it even harder to detect.
Argamal is a remote access Trojan (RAT), which means attackers can use it to remotely control the victim’s computer. Here’s just a short list of what it may entail:
Essentially, the infected computer turns into a remotely controlled machine. The owner may keep calmly going about their day, completely unaware that their device has been compromised. Yet the consequences of such an infection can be devastating.
For example, a single password stolen from a text note can lead to multiple compromised accounts at once if the victim reuses the same credentials across different sites. That’s why we recommend storing strong and unique passwords in an encrypted vault of a password manager rather than in plain text files.
Beyond hijacking accounts, the Trojan lets attackers literally spy on the user — reading their chats, digging into secret files, studying their sexual preferences… The cybercriminals can then use this highly sensitive information for subsequent attacks, blackmail, and extortion. We’ve covered what to do if you find yourself being targeted by extortionists in a previous post.
Another common scenario involves quietly stealing or substituting financial data — for instance, intercepting credentials from banking apps or replacing crypto-wallet addresses in the clipboard, which sends all your money straight to the attackers’ accounts.
In short, there’s a whole laundry list of ways attackers can exploit a victim’s device and data.
If you’ve decided to become the proud owner of “Waifu Simulator Ultra Definitive Edition”, stay on your guard:
In April 2026, we discovered a new malware campaign targeting players of “hentai” games. Once launched, the infected games install a previously unknown malicious implant on the user’s machine. After a few days, the implant downloads and executes a Trojan, resulting in full system compromise and broad remote control capabilities for the attackers. We dubbed this malware family “Argamal”.
The malware uses COM hijacking to persist on the victim’s machine, replacing the InprocServer32 entry for Windows Color System Calibration Loader DLL. This task is triggered when the user logs in, effectively allowing the malware to run at startup.
Kaspersky solutions detect this threat as Trojan.Win32.Termixia.*, Trojan.Win32.Agent.*, HEUR:Trojan.Win32.Argamal.gen and HEUR:Trojan-Downloader.Win32.Argamal.gen.
In April, as part of our ongoing monitoring of telemetry data, we found some suspicious DLLs. Further analysis revealed that various versions of these DLLs have existed since at least 2024.
The DLLs were spawned by different games written using various game engines and programming languages, including RenPy (Python) and RPG Maker MV (JavaScript), among others. However, they all had one thing in common: they were all hentai games. We searched for the distribution sources and found a number of websites hosting game screenshots and download links. These links redirected users to PixelDrain, a free file transfer service.
Adult games catalogue
In addition to these websites, the trojanized games have also been distributed via different torrent trackers, including AniRena.
Malicious game torrent in AniRena
Both the dedicated websites and torrents delivered an archive containing the infected game.
Contents of the game archive
This archive contained fully functional, legitimate game files, as well as a modified FFmpeg DLL (SHA1: 42add9475e67a1ccc6a6af94b5475d3defc01b85), that imported the DllGetClassObject function from a file called natives2_blob.bin. Since the game needs ffmpeg.dll to run properly, the library loads as soon as the user starts the game.
The natives2_blob.bin (SHA1: edce72f59e4c1d136cd1946af70d334c19df858d) file is a DLL that executes a Base64-encoded PowerShell script when loaded.
The natives2_blob.bin file code
This PowerShell script, which we’ll call Stage1, performs basic checks for controlled environments. For example, it checks for the Sandboxie folder in Program Files and Procmon64 in the process list. If all the checks indicate that the process is not running in a controlled environment, it proceeds to establish persistence.
Stage1 sets the MI_V environment variable (and also MI_V2 in the new versions of malware) for the current user to another Base64-encoded PowerShell script, which we’ll call Stage2. After that, it sets the InprocServer32 registry key at HKCU\SOFTWARE\Classes\CLSID\{722D0F89-B69C-4700-AE8C-4A44350E4876} to a random DLL file name in a random subdirectory of %USER%\AppData\Local, as well as the ShellFolder subkey to another random DLL file name in the same location. Stage1 also creates a scheduled task that will execute three days later. This task executes Stage2 and runs once.
Stage2 is a payload downloader script. It takes previously generated DLL filenames from the registry and downloads an encrypted payload called zaesdl.dat from GitHub using bitsadmin.exe. The downloaded payload is saved in the settings.dat file in the randomly chosen subdirectory of %USER%\AppData\Local. Stage2 decrypts it using AES-CBC with the key zbcd1j9234r670eh and an IV equal to the key. The decrypted payload is then saved in the DLL file specified in the ShellFolder registry subkey.
The decrypted payload is set as InprocServer32 at HKCU\SOFTWARE\Classes\CLSID\{B210D694-C8DF-490D-9576-9E20CDBC20BD}, which is a COM object used by the \Microsoft\Windows\WindowsColorSystem\Calibration Loader scheduled task. This task runs every time a user logs in, allowing the malware to run during every user session.
Before quitting, Stage2 also removes the changes made under the HKCU\SOFTWARE\Classes\CLSID\{722D0F89-B69C-4700-AE8C-4A44350E4876} registry key, unsets the MI_V environment variable (and MI_V2 in newer versions), and removes the scheduled task that launched Stage2.
Early payload versions decrypted themselves using the 0xB0C1D4E9 rolling XOR key, where the decryption key for the i + 1 block is the encrypted content of the i block (each encrypted block being four bytes long). The most recent agent versions don’t do that.
The samples we found had string encryption; they use a simple substitution with a key that corresponds position-by-position to the following alphabet: ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789@#$./:<>*&~. The decryption process involves finding the position of each symbol of the encrypted strings in the key, and replacing it with the symbol that occupies the same position in the alphabet.
During our investigation, we found the following keys were used:
All symbols not used in the key remain unchanged.
String decryption
The payload checks for the presence of the following security solutions using the output of the tasklist command:
Security solution detection logic
The payload itself is a RAT with broad functionality. The default C2 server is asper1[.]freeddns[.]org for earlier versions and Winst0[.]kozow[.]com for the latest versions of the payload. Both domains point to 186[.]158.223.35. We also saw another IP address for the first C2 in pDNS records, though we haven’t actually seen it in use. The C2 address can change based on a C2 reply or when certain conditions are met. For example, if the user’s default locale is set to “zh-CN”, the RAT sets its C2 address to country1[.]ignorelist[.]com. During most of our investigation, this domain pointed to 127[.]0.0.1, but starting April 26, it has been pointing to 186[.]158.223.35 as well.
The payload sends UDP heartbeats to port 57441 of the C2 server. These heartbeats contain information about detected security solutions, system startup time, time since last input activity, architecture info, machine IP address and username.
The C2 may respond to the heartbeat. Based on this response, the payload can perform different actions. Below is the full list of available commands.
| Response first byte | Description |
| 0x31 | Run DLL on the system |
| 0x57 | Send UDP request to the specified address |
| 0x55 | Open file or link from the response |
| 0x50 | Collect information about the infected system (e.g. process list and architecture) |
| 0x53 | Execute command from the response using ShellExecuteW |
| 0x52 | Run the file specified in the response using WinExec |
| 0x42 | Delete the file specified in the response |
| 0x41 | Update C2 domain |
| 0x59 | Get new payload: connect to C2 port 63559/UDP, get new DLL and update COM path in the registry |
The C2 can also set a flag in the response that will turn on the extended RAT mode. In this mode, the payload communicates with the C2 server using the 3747/tcp port.
TCP communications are encrypted using a simple substitution cipher. Each character is replaced using a fixed mapping defined by the key:
koP]Y4Os-_t?cB',aK.Wm>QM2[U!^C`*@Ff:X\6Dp8H%ATydE<e(#G&LhwRZ5znjJqgNrl)I7V$3=910"+Svxi/;ub
This key corresponds position-by-position to the standard ASCII character sequence:
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}In other words, each character in the ASCII set is replaced by the corresponding character in the key string.
C2 requests and responses are divided into two parts by the first space character. The first part is a command and the second part is usually an argument.
After connecting and before receiving information from the C2, the malware sends metadata about the infected machine using the NOOP command. This metadata includes a run cycle counter, mounted drive metadata, time since the last input activity and data about the display settings.
Based on the C2 command, the malware can execute commands on the infected machine, perform reboot and shutdown actions, control the cursor, take screenshots, compress files into archives, and send files to other specified servers. In short, it can fully control the machine. The full list of commands is as follows:
System control
KILL REBOOT: Reboots the infected systemKILL POWER: Shuts down the infected systemKILL SELF: Same as the QUIT command (described below)KILL ME: Exits process running the malwareSurveillance
SCREEN / SCREEN9: makes a screenshot, saves it to the ~wra1269.tmp file and sends it to the C2File operations
DELETE <filename>: deletes specified fileDELDIR <dirname>: deletes specified directoryREN <file path 1>#<file path 2>: moves specified fileMAKDIR <path>: creates directoryZIPFILE <file or folder name> / ZIPFOLDER <file or folder name>: compresses specified file/folder into a .zip archiveTAR <file or folder name> / TAR2 <file or folder name>: compresses specified file/folder into a .tar archiveGETFILEDATE <filename>: sends file’s last modification dateSETFILEDATE <filename>: sets file’s last modification dateGETFILEACC <filename>: sends file’s last access dateDWLOAD <filename>: sends file to the C2UPLOAD <filename>#<C2 address>: uploads file to the specified C2 serverReconnaissance
USER: sends usernameKALIVE: sends run cycle counterIDLE: sends number of seconds passed since last input activityDRIVES: sends information about mounted drivesFOLDEX <folder type>: sends full path to a directory of the specified type:0x63: temporary directory0x64: \Google\Chrome\User Data\Default\ in AppData\Local folder0x65: \Downloads\ in user home directory0x66: \Microsoft\Excel\XLSTART\ in AppData folder0x67: AppData folderLFILES <folder path>: lists and sends paths to all files in the directoryOSVER: sends information about user, hostname, OS architecture and versionCOMPILERDATE: sends constant hardcoded in the RAT, e.g., 25.10.2025Generic control
DSOCKE: recreates TCP keep-alive socketQUIT: notifies the C2 about quitting, closes the socket and stops the processRUNHID <command> / RUN <command>: runs specified command inside ShellExecuteWRUNDOS <command>: runs specified command inside CreateProcessWRUNTASK <command>: creates, runs and deletes task that executes specified commandSKEY <key code>: presses specified keyMOUSE FREEZE: freezes mouse movementMOUSE <command>: clicks the specified mouse button or sets the cursor position to the specified coordinatesDuring our research, we also observed other delivery methods for the RAT. Instead of patching FFmpeg and downloading the payload from GitHub, the attackers included the main payload as libpython64.dat or another file with a similar name in the lib\py3-windows-x86_64 directory of the game. This .dat file was loaded by one of the libraries used in the game, which was patched for this purpose.
In another case, the threat actor posted their malicious DLL file (payload downloader) on a gaming forum, disguising it as a cheat.
Our research revealed the following infrastructure was used in this attack.
| Domain | IP | First seen | ASN |
| asper1[.]freeddns[.]org | 181[.]116.218.56 | September 16, 2024 | 11664 |
| 186[.]158.223.35 | July 01, 2025 | 11664 | |
| country1[.]ignorelist[.]com | 186[.]158.223.35 | September 10, 2025 | 11664 |
| 127[.]0.0.1 | November 11, 2025 | – | |
| Winst0.kozow[.]com | 186[.]158.223.35 | April 26, 2026 | 11664 |
According to our telemetry, hundreds of individuals were infected with this malware. The majority of the victims were located in Russia, Brazil, Germany and Vietnam.
Based on the language of the comments in the code, infrastructure data and other facts we assess with medium confidence that the developer of the downloader chain speaks Spanish.
The actor behind this attack uses Spanish in variable names and comments. For example, the Base64-decoded delivery script contains the following lines:
Part of the PowerShell script used in the payload delivery
In addition, the JavaScript code from the website distributing infected games contains variable names, function names and comments in Spanish:
JavaScript code from the malicious site
Notably, the malware payloads used in this attack had previously chosen 127.0.0.1 as their C2 server when the victim’s default locale is set to “zh-CN”, thus not targeting Chinese users. This may indicate that the attacker is associated with a Chinese-speaking threat actor or uses payloads developed by a Chinese-speaking threat actor. However, we still believe it’s unlikely that the developer of these delivery chains is Chinese-speaking.
The Argamal Trojan is a new RAT targeting individuals who seek adult games. During our analysis, we observed a steady stream of updates to the payload, including the addition of new features and fixes for various bugs, as well as changes to the infrastructure. This leads us to believe that the threat actor behind this malware will continue to develop and enhance it. The campaign’s goal is likely data and credential theft; however, the RAT enables the attacker to take full control of the device and execute any malicious activity they want.
Creating malware in today’s development landscape has become significantly easier thanks to the wide availability of detailed guides, tooling, and automation resources. As a result, it is crucial not only to detect known malware but also to identify new and evolving threats as they emerge. Kaspersky solutions prevented the malicious activity in the earliest stages of the attack. The solutions help ensure device security by identifying not only known threats but also the behavior of the software and its actions, providing comprehensive protection against malware.
File hashes
RAT payloads:
76253fb55aed707440e808ea78e7101318436b1c
1405a3c5e0aeb08012484134e16cdec4ab29b4a4
535f4337f261b6da20a3c614eb13270bed2d533a
d2cb0d7a9ad2b5d4ea7c2da8aec62beb37cf36d6
e05f1767c2a337910ed75e90288838d6d0541164
dad26f61da7b8bccc78364411812be74c025b475
29f1d346a6e71774c7dad25b90f446b2974393df
e815a9b418d09c2d4bcd074c2c0bc21406eeb22f
17f8f8f34dfa737f36182fed7ff9e9814a114058
954722b0c9c678b1313d1f8b204e102842dc5889
69331cfdac792dc79240e6a6bb6e803eabd70beb
901cfa97b1baaf908fd4a02bb52d970f576c4193
5f1f3689bcf23de1b280b5f35712946da0f7978f
c2d9d48b3b10bd58cdf5df9463e3ffcd60533ff3
2423a5bf0fa7cb9ec09211630a5488629499691b
ae4601a19d28332a3ec6ac31b385cdf53be53450
Trojan downloaders:
9803604ec45f31f9ef75bcca1e1310d8ac1fc3a6
edce72f59e4c1d136cd1946af70d334c19df858d
02819d200d1424882af81cb504b3e8614b32397a
Domains and IPs
asper1[.]freeddns[.]org
Winst0[.]kozow[.]com
Country1[.]ignorelist[.]com
186[.]158.223.35
GitHub repositories used in the campaign
hxxps://github[.]com/gmz159/u
hxxps://github[.]com/DnyP/files
hxxps://github[.]com/mgzv/p
In April 2026, we discovered a new malware campaign targeting players of “hentai” games. Once launched, the infected games install a previously unknown malicious implant on the user’s machine. After a few days, the implant downloads and executes a Trojan, resulting in full system compromise and broad remote control capabilities for the attackers. We dubbed this malware family “Argamal”.
The malware uses COM hijacking to persist on the victim’s machine, replacing the InprocServer32 entry for Windows Color System Calibration Loader DLL. This task is triggered when the user logs in, effectively allowing the malware to run at startup.
Kaspersky solutions detect this threat as Trojan.Win32.Termixia.*, Trojan.Win32.Agent.*, HEUR:Trojan.Win32.Argamal.gen and HEUR:Trojan-Downloader.Win32.Argamal.gen.
In April, as part of our ongoing monitoring of telemetry data, we found some suspicious DLLs. Further analysis revealed that various versions of these DLLs have existed since at least 2024.
The DLLs were spawned by different games written using various game engines and programming languages, including RenPy (Python) and RPG Maker MV (JavaScript), among others. However, they all had one thing in common: they were all hentai games. We searched for the distribution sources and found a number of websites hosting game screenshots and download links. These links redirected users to PixelDrain, a free file transfer service.
Adult games catalogue
In addition to these websites, the trojanized games have also been distributed via different torrent trackers, including AniRena.
Malicious game torrent in AniRena
Both the dedicated websites and torrents delivered an archive containing the infected game.
Contents of the game archive
This archive contained fully functional, legitimate game files, as well as a modified FFmpeg DLL (SHA1: 42add9475e67a1ccc6a6af94b5475d3defc01b85), that imported the DllGetClassObject function from a file called natives2_blob.bin. Since the game needs ffmpeg.dll to run properly, the library loads as soon as the user starts the game.
The natives2_blob.bin (SHA1: edce72f59e4c1d136cd1946af70d334c19df858d) file is a DLL that executes a Base64-encoded PowerShell script when loaded.
The natives2_blob.bin file code
This PowerShell script, which we’ll call Stage1, performs basic checks for controlled environments. For example, it checks for the Sandboxie folder in Program Files and Procmon64 in the process list. If all the checks indicate that the process is not running in a controlled environment, it proceeds to establish persistence.
Stage1 sets the MI_V environment variable (and also MI_V2 in the new versions of malware) for the current user to another Base64-encoded PowerShell script, which we’ll call Stage2. After that, it sets the InprocServer32 registry key at HKCU\SOFTWARE\Classes\CLSID\{722D0F89-B69C-4700-AE8C-4A44350E4876} to a random DLL file name in a random subdirectory of %USER%\AppData\Local, as well as the ShellFolder subkey to another random DLL file name in the same location. Stage1 also creates a scheduled task that will execute three days later. This task executes Stage2 and runs once.
Stage2 is a payload downloader script. It takes previously generated DLL filenames from the registry and downloads an encrypted payload called zaesdl.dat from GitHub using bitsadmin.exe. The downloaded payload is saved in the settings.dat file in the randomly chosen subdirectory of %USER%\AppData\Local. Stage2 decrypts it using AES-CBC with the key zbcd1j9234r670eh and an IV equal to the key. The decrypted payload is then saved in the DLL file specified in the ShellFolder registry subkey.
The decrypted payload is set as InprocServer32 at HKCU\SOFTWARE\Classes\CLSID\{B210D694-C8DF-490D-9576-9E20CDBC20BD}, which is a COM object used by the \Microsoft\Windows\WindowsColorSystem\Calibration Loader scheduled task. This task runs every time a user logs in, allowing the malware to run during every user session.
Before quitting, Stage2 also removes the changes made under the HKCU\SOFTWARE\Classes\CLSID\{722D0F89-B69C-4700-AE8C-4A44350E4876} registry key, unsets the MI_V environment variable (and MI_V2 in newer versions), and removes the scheduled task that launched Stage2.
Early payload versions decrypted themselves using the 0xB0C1D4E9 rolling XOR key, where the decryption key for the i + 1 block is the encrypted content of the i block (each encrypted block being four bytes long). The most recent agent versions don’t do that.
The samples we found had string encryption; they use a simple substitution with a key that corresponds position-by-position to the following alphabet: ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789@#$./:<>*&~. The decryption process involves finding the position of each symbol of the encrypted strings in the key, and replacing it with the symbol that occupies the same position in the alphabet.
During our investigation, we found the following keys were used:
All symbols not used in the key remain unchanged.
String decryption
The payload checks for the presence of the following security solutions using the output of the tasklist command:
Security solution detection logic
The payload itself is a RAT with broad functionality. The default C2 server is asper1[.]freeddns[.]org for earlier versions and Winst0[.]kozow[.]com for the latest versions of the payload. Both domains point to 186[.]158.223.35. We also saw another IP address for the first C2 in pDNS records, though we haven’t actually seen it in use. The C2 address can change based on a C2 reply or when certain conditions are met. For example, if the user’s default locale is set to “zh-CN”, the RAT sets its C2 address to country1[.]ignorelist[.]com. During most of our investigation, this domain pointed to 127[.]0.0.1, but starting April 26, it has been pointing to 186[.]158.223.35 as well.
The payload sends UDP heartbeats to port 57441 of the C2 server. These heartbeats contain information about detected security solutions, system startup time, time since last input activity, architecture info, machine IP address and username.
The C2 may respond to the heartbeat. Based on this response, the payload can perform different actions. Below is the full list of available commands.
| Response first byte | Description |
| 0x31 | Run DLL on the system |
| 0x57 | Send UDP request to the specified address |
| 0x55 | Open file or link from the response |
| 0x50 | Collect information about the infected system (e.g. process list and architecture) |
| 0x53 | Execute command from the response using ShellExecuteW |
| 0x52 | Run the file specified in the response using WinExec |
| 0x42 | Delete the file specified in the response |
| 0x41 | Update C2 domain |
| 0x59 | Get new payload: connect to C2 port 63559/UDP, get new DLL and update COM path in the registry |
The C2 can also set a flag in the response that will turn on the extended RAT mode. In this mode, the payload communicates with the C2 server using the 3747/tcp port.
TCP communications are encrypted using a simple substitution cipher. Each character is replaced using a fixed mapping defined by the key:
koP]Y4Os-_t?cB',aK.Wm>QM2[U!^C`*@Ff:X\6Dp8H%ATydE<e(#G&LhwRZ5znjJqgNrl)I7V$3=910"+Svxi/;ub
This key corresponds position-by-position to the standard ASCII character sequence:
!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}In other words, each character in the ASCII set is replaced by the corresponding character in the key string.
C2 requests and responses are divided into two parts by the first space character. The first part is a command and the second part is usually an argument.
After connecting and before receiving information from the C2, the malware sends metadata about the infected machine using the NOOP command. This metadata includes a run cycle counter, mounted drive metadata, time since the last input activity and data about the display settings.
Based on the C2 command, the malware can execute commands on the infected machine, perform reboot and shutdown actions, control the cursor, take screenshots, compress files into archives, and send files to other specified servers. In short, it can fully control the machine. The full list of commands is as follows:
System control
KILL REBOOT: Reboots the infected systemKILL POWER: Shuts down the infected systemKILL SELF: Same as the QUIT command (described below)KILL ME: Exits process running the malwareSurveillance
SCREEN / SCREEN9: makes a screenshot, saves it to the ~wra1269.tmp file and sends it to the C2File operations
DELETE <filename>: deletes specified fileDELDIR <dirname>: deletes specified directoryREN <file path 1>#<file path 2>: moves specified fileMAKDIR <path>: creates directoryZIPFILE <file or folder name> / ZIPFOLDER <file or folder name>: compresses specified file/folder into a .zip archiveTAR <file or folder name> / TAR2 <file or folder name>: compresses specified file/folder into a .tar archiveGETFILEDATE <filename>: sends file’s last modification dateSETFILEDATE <filename>: sets file’s last modification dateGETFILEACC <filename>: sends file’s last access dateDWLOAD <filename>: sends file to the C2UPLOAD <filename>#<C2 address>: uploads file to the specified C2 serverReconnaissance
USER: sends usernameKALIVE: sends run cycle counterIDLE: sends number of seconds passed since last input activityDRIVES: sends information about mounted drivesFOLDEX <folder type>: sends full path to a directory of the specified type:0x63: temporary directory0x64: \Google\Chrome\User Data\Default\ in AppData\Local folder0x65: \Downloads\ in user home directory0x66: \Microsoft\Excel\XLSTART\ in AppData folder0x67: AppData folderLFILES <folder path>: lists and sends paths to all files in the directoryOSVER: sends information about user, hostname, OS architecture and versionCOMPILERDATE: sends constant hardcoded in the RAT, e.g., 25.10.2025Generic control
DSOCKE: recreates TCP keep-alive socketQUIT: notifies the C2 about quitting, closes the socket and stops the processRUNHID <command> / RUN <command>: runs specified command inside ShellExecuteWRUNDOS <command>: runs specified command inside CreateProcessWRUNTASK <command>: creates, runs and deletes task that executes specified commandSKEY <key code>: presses specified keyMOUSE FREEZE: freezes mouse movementMOUSE <command>: clicks the specified mouse button or sets the cursor position to the specified coordinatesDuring our research, we also observed other delivery methods for the RAT. Instead of patching FFmpeg and downloading the payload from GitHub, the attackers included the main payload as libpython64.dat or another file with a similar name in the lib\py3-windows-x86_64 directory of the game. This .dat file was loaded by one of the libraries used in the game, which was patched for this purpose.
In another case, the threat actor posted their malicious DLL file (payload downloader) on a gaming forum, disguising it as a cheat.
Our research revealed the following infrastructure was used in this attack.
| Domain | IP | First seen | ASN |
| asper1[.]freeddns[.]org | 181[.]116.218.56 | September 16, 2024 | 11664 |
| 186[.]158.223.35 | July 01, 2025 | 11664 | |
| country1[.]ignorelist[.]com | 186[.]158.223.35 | September 10, 2025 | 11664 |
| 127[.]0.0.1 | November 11, 2025 | – | |
| Winst0.kozow[.]com | 186[.]158.223.35 | April 26, 2026 | 11664 |
According to our telemetry, hundreds of individuals were infected with this malware. The majority of the victims were located in Russia, Brazil, Germany and Vietnam.
Based on the language of the comments in the code, infrastructure data and other facts we assess with medium confidence that the developer of the downloader chain speaks Spanish.
The actor behind this attack uses Spanish in variable names and comments. For example, the Base64-decoded delivery script contains the following lines:
Part of the PowerShell script used in the payload delivery
In addition, the JavaScript code from the website distributing infected games contains variable names, function names and comments in Spanish:
JavaScript code from the malicious site
Notably, the malware payloads used in this attack had previously chosen 127.0.0.1 as their C2 server when the victim’s default locale is set to “zh-CN”, thus not targeting Chinese users. This may indicate that the attacker is associated with a Chinese-speaking threat actor or uses payloads developed by a Chinese-speaking threat actor. However, we still believe it’s unlikely that the developer of these delivery chains is Chinese-speaking.
The Argamal Trojan is a new RAT targeting individuals who seek adult games. During our analysis, we observed a steady stream of updates to the payload, including the addition of new features and fixes for various bugs, as well as changes to the infrastructure. This leads us to believe that the threat actor behind this malware will continue to develop and enhance it. The campaign’s goal is likely data and credential theft; however, the RAT enables the attacker to take full control of the device and execute any malicious activity they want.
Creating malware in today’s development landscape has become significantly easier thanks to the wide availability of detailed guides, tooling, and automation resources. As a result, it is crucial not only to detect known malware but also to identify new and evolving threats as they emerge. Kaspersky solutions prevented the malicious activity in the earliest stages of the attack. The solutions help ensure device security by identifying not only known threats but also the behavior of the software and its actions, providing comprehensive protection against malware.
File hashes
RAT payloads:
76253fb55aed707440e808ea78e7101318436b1c
1405a3c5e0aeb08012484134e16cdec4ab29b4a4
535f4337f261b6da20a3c614eb13270bed2d533a
d2cb0d7a9ad2b5d4ea7c2da8aec62beb37cf36d6
e05f1767c2a337910ed75e90288838d6d0541164
dad26f61da7b8bccc78364411812be74c025b475
29f1d346a6e71774c7dad25b90f446b2974393df
e815a9b418d09c2d4bcd074c2c0bc21406eeb22f
17f8f8f34dfa737f36182fed7ff9e9814a114058
954722b0c9c678b1313d1f8b204e102842dc5889
69331cfdac792dc79240e6a6bb6e803eabd70beb
901cfa97b1baaf908fd4a02bb52d970f576c4193
5f1f3689bcf23de1b280b5f35712946da0f7978f
c2d9d48b3b10bd58cdf5df9463e3ffcd60533ff3
2423a5bf0fa7cb9ec09211630a5488629499691b
ae4601a19d28332a3ec6ac31b385cdf53be53450
Trojan downloaders:
9803604ec45f31f9ef75bcca1e1310d8ac1fc3a6
edce72f59e4c1d136cd1946af70d334c19df858d
02819d200d1424882af81cb504b3e8614b32397a
Domains and IPs
asper1[.]freeddns[.]org
Winst0[.]kozow[.]com
Country1[.]ignorelist[.]com
186[.]158.223.35
GitHub repositories used in the campaign
hxxps://github[.]com/gmz159/u
hxxps://github[.]com/DnyP/files
hxxps://github[.]com/mgzv/p
Last week on Malwarebytes Labs:
Stay safe!
We don’t just report on threats—we remove them
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
Last week on Malwarebytes Labs:
Stay safe!
We don’t just report on threats—we remove them
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
Over the past few months, we have conducted an in-depth analysis of specific activity clusters of Kimsuky (aka APT43, Ruby Sleet, Black Banshee, Sparkling Pisces, Velvet Chollima, and Springtail), a prolific Korean-speaking threat actor. Our research revealed notable tactical shifts throughout multiple phases of the group’s latest campaigns.
Kimsuky has continuously introduced new malware variants based on the PebbleDash platform, a tool historically leveraged by the Lazarus Group but appropriated by Kimsuky since at least 2021. Our monitoring indicates various strategic updates to the group’s arsenal, including the use of VSCode Tunneling, Cloudflare Quick Tunnels, DWAgent, large language models (LLMs), and the Rust programming language. This expanding set of tools underscores the group’s ongoing adaptation and evolution.
Specifically, Kimsuky leveraged legitimate VSCode tunneling mechanisms to establish persistence and distributed the open-source DWAgent remote monitoring and management tool for post-exploitation activities. These activities affected various sectors in South Korea, impacting both public and private entities.
This article covers both previously undocumented attacks and a deeper technical analysis of incidents within this campaign that have been reported before — offering new insight beyond what has already been published.
First identified by Kaspersky in 2013, Kimsuky has been active for over 10 years and is considered less technically proficient compared to other Korean-speaking APT groups. The group has targeted a wide range of entities and demonstrated capability in creating tailored spear-phishing emails. The group’s arsenal includes proprietary malware such as PebbleDash, BabyShark, AppleSeed, and RandomQuery, as well as open-source RATs like xRAT, XenoRAT, and TutRAT. This blog post examines the evolving PebbleDash-based malware (referred to as the PebbleDash cluster) and its connections to the AppleSeed-based malware (referred to as the AppleSeed cluster).
The PebbleDash and AppleSeed clusters are considered the most technically advanced in Kimsuky’s toolset. Since at least 2019, these clusters have masqueraded as legitimate documents and application installers, manifesting as JSE droppers or executables with .EXE, .SCR and .PIF extensions. Both are particularly adept at establishing backdoors and stealing information, and ongoing development of their variants has been observed. They even occasionally utilize stolen legitimate certificates from South Korean organizations to avoid detection.
Timeline of the AppleSeed and PebbleDash malware families
AppleSeed and PebbleDash have primarily targeted the public and private sectors in South Korea. The PebbleDash cluster has shown a particular interest in the medical, military and defense industries worldwide. The PebbleDash cluster compromised Brazilian and South Korean defense organizations throughout the past several years, as well as a German defense firm. In 2024, the South Korean government released a security advisory regarding the AppleSeed cluster, detailing how the malware was distributed by replacing a security software installer required to access a construction entity’s website.
Kimsuky meticulously crafts and delivers spear-phishing emails to its targets in an attempt to entice them into opening attachments. According to recent research, the group also occasionally approaches targets by contacting them via messengers. In all cases, the initial contact leads to the delivery of a malicious attachment disguised as a document. These attachments often consist of compressed files containing droppers in formats such as .JSE, .EXE, .PIF, or .SCR. The filenames are consistent with the message content and are meant to convince the recipient to open the attachment. The malicious files are often disguised as product quotations, job offers, information guides, surveys, government documents, and personal photos.
Here are some recently discovered examples:
| Number | Filename | Filename (translated to English) | Detection date | MD5 | Malware deployed |
| 1 | [별지 제8호서식] 개인정보(열람 정정삭제 처리정지) 요구서(개인정보 보호법 시행규칙).hwp.jse | Appendix Form No. 8 – Request for Access, Correction, Deletion, and Suspension of Processing of Personal Information (PIPA Enforcement Rules).hwp.jse | August 28, 2025 | 995a0a49ae4b244928b3f67e2bfd7a6e | HelloDoor |
| 2 | 2026년 상반기 국내대학원 석사야간과정 위탁교육생 선발관련 서류.hwpx.jse | Documents for the Selection of Commissioned Students for Domestic Graduate School Master’s Evening Programs (H1 2026).hwpx.jse | December 14, 2025 | 52f1ff082e981cbdfd1f045c6021c63f | httpMalice |
| 3 | security_20260126.scr | – | January 26, 2026 | 65fc9f06de5603e2c1af9b4f288bb22c | Reger Dropper, MemLoad, httpTroy |
| 4 | 노현정님.pdf.jse | Ms. Noh Hyun-jung.pdf.jse | January 28, 2026 | 8e15c4d4f71bdd9dbc48cd2cabc87806 | AppleSeed chain |
| 5 | 대국민서비스관리운영체계현장점검증적(초안).pif | On-site Inspection Evidence for the Public Service Management System (Draft).pif | February 5, 2026 | 8983ffa6da23e0b99ccc58c17b9788c7 | Pidoc Dropper, HappyDoor |
JSE droppers contain a minimum of two Base64-encoded blobs: one serving as a benign lure file and one or more containing malicious code. Additional blobs may exist within the dropper, but they are unused. The two blobs are decoded using JScript and stored in an arbitrary location on disk, such as C:\ProgramData, with the malicious filenames randomly generated according to the scheme [random]{7}.[random]{4}. The lure file is opened immediately. The malicious payload leverages powershell.exe -windowstyle hidden certutil -decode [src path] [dst path] for the second Base64 decoding before execution. Ultimately, the malicious payload is executed via command-line instructions such as regsvr32.exe /s [file path] or rundll32.exe [file path] [export function].
Reger Dropper (.SCR) and Pidoc Dropper (.PIF) also contain benign lure files and malicious payloads that, in both cases, are encrypted using XOR operations. Specifically, Reger Dropper employs a hard-coded key #RsfsetraW#@EsfesgsgAJOPj4eml;, while Pidoc Dropper utilizes single-byte XOR with 0xFF to decrypt the internal data for execution. Pidoc Dropper is fully obfuscated using dummy data and encrypted strings. Both droppers deploy files in specific directories such as %temp% or C:\ProgramData before executing the malware using regsvr32.exe.
In addition to these droppers, Kimsuky employed a variety of executable droppers, including those crafted in Go or packaged with Inno Setup.
In this section, we describe several malware families recently dropped by the droppers discussed above.
Written in Rust, a programming language rarely used by Kimsuky, HelloDoor is a DLL-based backdoor first identified in August 2025. It is deployed via a malicious JSE dropper. Since it has limited capabilities and a simplistic communication mechanism, the backdoor is most probably in the early stages of development. Nevertheless, it is noteworthy that HelloDoor employs a C2 server hosted through TryCloudflare, a temporary tunneling service provided by Cloudflare. This service allows users to expose a local web service to the internet with no setup or account, making the infrastructure behind it difficult to trace.
HelloDoor establishes persistence upon execution by registering itself to the HKCU\Software\Microsoft\Windows\CurrentVersion\Run key with the value name tdll and the command regsvr32.exe /s [current file path].
The implant communicates with the C2 server (hxxp://female-disorder-beta-metropolitan.trycloudflare[.]com/index.php) over the HTTP protocol. Depending on whether the process is executing with an elevated token, it binds to a specific local port: 5555 if the token is elevated, or 5554 if not. Before initiating communication, it generates a unique identifier by collecting device information, such as the MAC address, computer name, and the string “windows”, then computes a hash value from this information.
The malware then constructs a query string in the format aaaaaaaaaa=2&bbbbbbbbbb=[the unique identifier]&cccccccccc=1, which is a traditional format used across the PebbleDash cluster. Subsequent server responses are Base64-decoded and then decrypted using RC4 with the key fwr3errsettwererfs. The decrypted content contains command strings. Possible commands are:
| Command | Description |
| “mcd” | Set the current directory |
| “msleep” | Sleep for the provided time |
| “install” | Register the regsvr32.exe /s [the provided file path] command to the HKCU\Software\Microsoft\Windows\CurrentVersion\Run autorun registry using the install value name |
| [command] | Execute the provided command using chcp 65001 > nul & cmd /U /C [command] |
Though interesting, it is no longer surprising that we found comments in the code that appear to have been generated by an LLM service rather than a human developer. This is based on traces that include emojis used for logging debugging messages.
✅ Port is now listening (no accepting) ❌ Port is already in use 🔍 regsvr32.exe detected as parent. Attempting to terminate...
This is a common trait of LLM services that provides users with better visibility. We previously observed similar comments in the PowerShell-based stealer suite used by BlueNoroff. HelloDoor’s simple structure and the fact that no other Rust-based malware from the group has been discovered yet support our claim.
Even though the code is believed to have been developed using an LLM service, we still found some typos and grammatical errors, such as:
It is likely that the flawed comments were added manually before or after AI was used.
The latest PebbleDash-based backdoor, httpMalice, emerged no later than December 2025 and is deployed by the JSE Dropper. Although we found limited direct connections to both the AppleSeed and PebbleDash clusters, the malware is closer to PebbleDash. The following shared characteristics have been identified:
S-1-12-12288 SID, indicating a high integrity level – a feature also observed in PebbleDash and httpTroy.m= parameter in C2 communication.Our analysis revealed two distinct versions of httpMalice based on their C2 communications: version 1.9 communicates over HTTP and version 1.8 uses Dropbox. The latter, the older variant, leverages the Dropbox API by utilizing pre-defined application credentials. Unlike its predecessor, the HTTP variant employs HTTP/HTTPS protocols to interact with its C2 server and maintains persistent access to the victim device through a Windows service named CacheDB. This mirrors tactics observed in similar threats, such as httpSpy.
The more recent variant gathers critical information from the compromised system, such as the current directory path, volume serial numbers, user privileges, username, local IP address, and the name and size of the currently executed httpMalice DLL file. It then combines the root drive’s volume serial number with the user’s access token privilege level to create a unique identifier for each infected system, formatted as [volume serial]{8}_[elevation status].
| Value of elevation status | Description |
| 0 | Running under the SYSTEM account with an elevated token |
| 1 | Running under an elevated administrator account |
| 2 | Running without elevation |
Depending on the token privilege, the backdoor then establishes persistence by either creating a service or registering itself to autostart at user logon. If the token is elevated, a service named CacheDB is created that executes the command cmd.exe /c “rundll32.exe [current DLL path], load”. The service’s display name is set to Administrator, and its description is defined as CacheDB Service. If the token is not elevated, the backdoor registers the same command under the registry key HKCU\Software\Microsoft\Windows\CurrentVersion\Run with the value name Everything 1.9a-[filesize]. The older version used Everything 1.8a-[filesize] as a value name.
The latest version can execute a combination of Windows commands by default to perform host profiling, while the older version fetches the command set from Dropbox. In httpMalice, commands are mostly executed using the format cmd.exe /c chcp 949 [command] > [temporary filename], which redirects the output to separate files, with the consistent prefix 2Ato6478s added to their names. The chcp 949 command changes the code page to 949, indicating that the malware targets users of the Korean language (EUC-KR charset).
Windows commands used to gather system details
httpMalice transmits the result of host profiling to its C2 server as a URL parameter, using the POST method over the HTTP/HTTPS protocol, with the header x-www-form-urlencoded. The URL includes two or three parameters: operation mode, unique identifier (referred to as UID), and data. The operation mode, or parameter m, supports the following values:
| Value | Description |
| 1 | Send the session identifier (parameter s) along with the current state (parameter a) |
| 2 | Request command |
| 3 | Send result after executing the command (parameter d) |
| 8 | Request directory to be archived and sent |
| 9 | Send the archived directory |
| 10 | Send a message like “.cmd” or “.tmp” (parameter d) |
| 11 | Send ping |
| 12 | Send the captured screenshot (parameter d) |
| 13 | Send the infected device information (parameter d) |
As shown in the table above, the mode is set to 13 at the host profiling stage. The UID is formatted as [volume serial]{8}_[elevation status], and the data contains the ChaCha20-encrypted and Base64-encoded output of the command set stored in the temporary file. The resulting URL format is: m=13&u=[volume serial]{8}_[elevation status]&d=[Chacha20 encrypted + Base64-encoded data to be sent].
The key and nonce used for ChaCha20 encryption are derived from the pointer address of the buffer, resulting in nearly randomized keys. To ensure proper decryption on the attacker side, the nonce and key values are appended after the encrypted data, and the combined blob is then Base64-encoded. The counter is initialized to 0. The following figure illustrates how the encrypted data is structured after performing Base64 decoding.
Structure of the ChaCha20-encrypted data blob
After sending the host profiling data, the backdoor continuously transmits a screen capture with mode 12 and a ping message with mode 11. Finally, it sends a session identifier, which is a combination of the current username and local IP address separated by an ‘@’ symbol. In this case, the mode is set to 1 and the a parameter (current state) is set to 0, indicating that the C2 operation has been activated. The following table provides other possible values of the a parameter:
| Value | Description |
| 0 | httpMalice has been activated |
| 1 | httpMalice has been inactivated (upon command 9) |
| 2 | httpMalice has been removed (upon command 8) |
The whole process from sending the host profile to the backdoor activation repeats every two minutes until the C2 server returns a “success!” message.
C2 communication sequence of httpMalice
When the backdoor receives the message from the C2 server, it creates two threads dedicated to processing commands and sending the current state, including the session identifier. The first thread receives a command from the C2 server. It requests a command by sending mode 2 and, if successful, immediately sends mode 10 along with the string “.cmd” in the d parameter.
The commands supported by httpMalice are as follows:
| Command | Description |
| 0 | Do nothing |
| 1 | Execute the command with EUC-KR encoding |
| 2 | Download and extract the file to the infected device |
| 3 | Upload a directory to the C2 server after it has been archived |
| 5 | Get the current directory |
| 6 | Set the current directory |
| 7 | Execute the command without setting a EUC-KR character set |
| 8 | Remove its persistence traces and exit the process |
| 9 | Hibernate |
| 10 | Execute the command using the provided session ID |
| 12 | Capture the screen |
| 13 | Load the downloaded payload into memory |
Since early 2025, we have observed several versions of MemLoad; specifically, MemLoad V2 emerged in March, and V3 appeared by September. The payload that began being deployed through the Reger Dropper this year has been identified as an updated variant of MemLoad, slightly modified from the V3 version (referred to internally as MemLoader.dll).
Kimsuky leverages MemLoad to evade detection of its final backdoor and to carefully assess the value of targeted systems through anti-VM checks and reconnaissance. Upon installation, it requests an additional payload from the C2 server, executing it reflectively in memory if deemed suitable. Notably, all versions of MemLoad V2 and later use the same RC4 key.
Below are the key operations of MemLoad:
C:\Windows\system32 directory. If successful, the ID starts with ‘A-‘ (indicating administrative privileges); otherwise, it starts with ‘U-‘.ChromeCheck, and the command
schtasks /create /tn <task name> /tr "regsvr32 /s <current file path>" /sc minute /mo 1 /rl highest /f is executed. Otherwise, the task is named EdgeCheck, and the command
schtasks /create /tn <task name> /tr "regsvr32 /s <current file path>" /sc minute /mo 1 /f is executed.Authorization: Bearer {ID} or X-Browser-Validation: {ID} for authentication. The ID is set to the previously generated ID value.#RsfsetraW#@EsfesgsgAJOPj4eml;. The decrypted payload is then reflectively loaded into memory, and its hello export function is invoked.The payload downloaded and executed by MemLoad is identified as the httpTroy backdoor. This backdoor serves as the primary role for long-term access and data exfiltration. Similar to MemLoad, it employs stealth techniques by creating a flag file and writing eight random bytes to it. However, in this case the file is created at [current file path]:HUI in the ADS (Alternative Data Stream) area. The backdoor then checks its privileges to determine if it is elevated and assigns an ID value in the format A-[random-8-chars] or U-[random-8-chars].
Since Gen Digital covers httpTroy’s features and functionality in detail elsewhere, we will not provide a thorough explanation here to avoid redundancy. Instead, we will simply note that it communicates with the C2 server at hxxps://file.bigcloud.n-e[.]kr/index.php.
AppleSeed first appeared in 2019 and reached version 3.0. However, we now only see version 2.1. It originally consisted of two components: a dropper and the main AppleSeed. Since 2022, the updated AppleSeed chain has involved two droppers, an additional component referred to as the installer, and the main payload. It is mostly delivered through JSE Dropper.
Updated AppleSeed infection chain
There are two versions of the main AppleSeed: Dropper and Spy. The Dropper variant is responsible for downloading additional malware and executing commands received from its C2 server, while the Spy version gathers sensitive information such as documents, screenshots, keystrokes, and lists of USB drives. A notable change in version 2.1 is the inclusion, since 2022, of collecting the C:\GPKI directory – functionality that is also implemented in Troll Stealer. This directory contains a digital certificate used by the South Korean government to securely authenticate public officials and government systems.
HappyDoor, an AppleSeed-based backdoor malware disclosed by AhnLab in 2024, is less visible than AppleSeed. HappyDoor shares several features with AppleSeed, including the same string obfuscation algorithm, the data types it collects, and the use of RSA encryption. Given these similarities, we assess with medium confidence that HappyDoor is an advanced variant evolved from AppleSeed.
We observed interesting post-exploitation activities involving VSCode and DWAgent. All of the observed VSCode droppers used the same lure files as the PebbleDash malware cluster. While we are unsure of the exact reason for this strategy, we suspect that the actor prepared both PebbleDash and VSCode droppers in anticipation of the PebbleDash infection chain being detected by security products because of its backdoor capabilities. In contrast, the use of VSCode is designed to have fewer detection points.
Since last year, Kimsuky has been leveraging the legitimate Visual Studio Code Remote Tunneling feature to establish covert remote access to the victim’s device, bypassing detection designed for traditional malware-based C2 channels (first described by Darktrace researchers). In these attacks, instead of dropping malware, the JSE dropper downloads a legitimate Visual Studio Code (VSCode) CLI onto the infected device. The script establishes persistence by creating a tunnel via the application, with the tunnel name “bizeugene”, using the command below.
The Remote Tunneling feature in VSCode supports establishing a tunnel using either a Microsoft or GitHub account. When the code tunnel command is executed, the CLI initiates an authentication flow and returns a login URL along with a device code. The user must then navigate to the URL, enter the device code, and authenticate with their account. Once authentication is successful, the tunnel is created and the CLI outputs a URL for tunneling that enables browser-based access to the remote host.
The GitHub authentication method is selected in this instance because GitHub is configured as the default provider in non-interactive execution contexts. By using echo |, the script injects a \r\n (Carriage Return and Line Feed) into the standard input stream, effectively confirming the default prompt selection without manual interaction. As a result, the CLI automatically initiates the GitHub authentication flow. Next, all CLI output that includes a login URL and a device code is saved to out.txt.
Out.txt content
The JScript code in the JSE dropper monitors the out.txt file for a URL that begins with hxxps://vscode[.]dev/tunnel. This URL contains the full address of the established tunnel. Once detected, the file content containing the URL and the device code is sent to a compromised legitimate South Korean website (hxxps://www.yespp.co[.]kr/common/include/code/out[.]php) using the HTTP POST method. The request contains the file contents in the application/x-www-form-urlencoded header data formatted as out=URLencoded{result of the command}&token=URLencoded{"bizeugene"}. After authentication is complete, the attacker can access the compromised host externally through a web browser by authenticating with their own GitHub account.
While searching our telemetry for artifacts related to a different infection, we identified a new VSCode tunnel installer written in Go. A previous version of this installer was implemented using JScript and was limited to secure channels because of its reliance on a specific tunnel name. The new variant, named vscode_payload by the developer based on the embedded Go path, is fully operational and supports every tunnel on each targeted device. It includes features that are nearly identical to those of the previous version, such as downloading, unarchiving, and executing the VSCode CLI.
| Number | Installer type | VSCode version | Download source |
| 1 | Written in JScript | VSCode CLI 1.106.3 | hxxps://vscode.download.prss.microsoft[.]com/dbazure/download/stable/bf9252a2fb45be6893dd8870c0bf37e2e1766d61/vscode_cli_win32_x64_cli[.]zip |
| 2 | Written in Go | VSCode CLI 1.106.2 | hxxps://vscode.download.prss.microsoft[.]com/dbazure/download/stable/1e3c50d64110be466c0b4a45222e81d2c9352888/vscode_cli_win32_x64_cli[.]zip |
After the VSCode CLI file has been successfully downloaded, it is unzipped into the C:\Users\Public directory, and the extracted code.exe is executed with the tunnel command.
This is how the installer works:
code.exe tunnel.0x1B 0x5B 0x42 (Down Arrow) and 0x0A (Enter) escape sequence to the pseudo-terminal, which enables tunnel creation via a GitHub account.0x0A escape sequence to the pseudo-terminal to use the current machine name as the identifier.The following figure illustrates the sequence for creating a tunnel using the VSCode CLI. Red boxes highlight the strings that the installer searches for. Yellow boxes indicate standard input operations sent from the installer using escape sequences. Sky blue boxes represent the values that are necessary to create the tunnel on the attacker’s side. (The “Microsoft Account” string in the second step is not shown in this figure because the second “GitHub Account” was already selected during the process.)
Creating a tunnel using VSCode CLI
Once the process is complete, the attacker can access the targeted host through the tunnel on their remote machine using their GitHub account via a browser or VSCode. The targeted device then begins communicating with Microsoft-owned servers without the user realizing that the communication is from an attacker.
An interesting feature of this variant is that it sends debugging messages and necessary values to a Slack channel via a WebHook. Upon execution, it sends "+++ I am started +++", as well as a heartbeat message "~~~ I am alive ~~~" approximately every second during tunneling authentication.
DWAgent is a remote administration tool that is frequently exploited by threat actors, including ransomware and APT groups, to easily access compromised endpoints with minimal risk of detection. Kimsuky is one of the threat actors that uses this tool in its operations.
We observed that the group delivered DWAgent in at least two ways. The first involved delivering a compressed file containing DWAgent, along with separate commands, to a host infected with httpMalice for installation. The second method involved creating a separate installer.
This installer is very similar to the Reger Dropper. It uses the same RC4 key and has a similar code structure. It includes an archived binary and a legitimate unrar.exe binary, both encrypted with RC4. When executed, the installer decrypts the archived binary and saves it as 1.zip in the C:\ProgramData directory. It also creates an unrar.exe file in the same location using the decrypted unrar.exe binary. The dropper then uses the command C:\programdata\unrar.exe x C:\programdata\1.zip C:\programdata\ to extract the contents of the ZIP file. Finally, it executes the commands necessary to install DWService as a service on the target host:
The compressed file contains a pre-packaged, ready-to-use DWAgent, as well as a predefined config file. The actor deployed the agent with a config.json file linked to their own account to covertly control the device. As a result, the remote session is immediately activated by the above command, granting the attacker control.
The predefined config file is as follows. Note that the servers are legitimate DWAgent relay servers.
{
"enabled": true,
"key": "kDRNGmWGTMpjQmREgQzU",
"listen_port": 7950,
"nodes": [
{
"id": "ND896147",
"port": "443",
"server": "node896147.dwservice[.]net"
},
{
"id": "ND828765",
"port": "443",
"server": "node828765.dwservice[.]net"
},
{
"id": "ND484265",
"port": "443",
"server": "node484265.dwservice[.]net"
}
],
"password": "eJwrynEqD0r294twTXLKCHWqDPLPCql0Kg/JDqpIdk4HAKYMCso=",
"url_primary": "hxxps://www.dwservice[.]net/"
}
For years, Kimsuky has relied heavily on the South Korea-based free domain hosting service 내도메인[.]한국 (pronounced as “naedomain[.]hankook) to mimic legitimate sites with domains like .p-e.kr, .o-r.kr, .n-e.kr, .r-e.kr, and .kro.kr. This service has been utilized to create C2 servers for PebbleDash and AppleSeed clusters, and the background infrastructures have been mostly resolved to the virtual private servers belonging to InterServer. It has also been noted that many other malicious actors have exploited this free domain hosting service, so it alone cannot be considered proof of a connection to Kimsuky.
The actor also occasionally exploits South Korean websites as C2 servers to evade network-IoC-based detection and increase the success rate of attacks. Furthermore, they actively leverage tunneling services such as Cloudflare Quick Tunnels, VSCode Tunneling, and Ngrok to hide their infrastructure. These traits are mostly observed across the PebbleDash cluster.
We identified multiple infection logs uploaded to the Dropbox storage used for httpMalice’s C2 server. They were analyzed as having been stolen from infected systems across various organizations or individuals in South Korea. Notably, each victim’s folder contained a user.txt file with detailed information such as target details, the presence of something named “http” (possibly a backdoor, such as httpTroy or httpMalice), DWAgent existence, and relationships between infected devices and targets. While we could not verify the exact creation process of these files, they were likely created manually by attackers to manage victims using Korean words.
Below you can see an example of this type of file content. In this context, “장악” means “take over” and “있음” means “exists”.
[Target's name] [Description] [Infection date] 장악, http 있음, DWService 있음.
While both clusters have mainly focused on targeting the private and public sectors in South Korea, the AppleSeed malware cluster shows more interest in government entities. The PebbleDash cluster has also shown particular interest in the defense sector worldwide.
Over the past few years, we have observed two clusters using overlapping distribution methods – JSE, EXE, SCR, and PIF droppers. The targets are also increasingly aligning. Furthermore, we noted that several samples from both malware clusters were signed with the same stolen certificate and used identical mutex patterns. These findings suggest that a single actor is likely controlling both clusters and has the capability to modify code as needed. This concept was also described in another research paper at the Virus Bulletin conference.
Since its emergence, AppleSeed has been linked to Kimsuky operations, with each variant showing ties to the group. Since 2021, PebbleDash has been found exclusively in Kimsuky attacks. Based on our analysis of targets, infrastructure, and malware characteristics, we assess with medium-high confidence that attacks associated with these malware families are conducted by Kimsuky-affiliated clusters.
These two clusters share technical links to the threat actor known as Ruby Sleet, one of the names Microsoft uses for Kimsuky activity. In previous reports, Mandiant also referred to these clusters as Cerium, but now they appear to consider them part of the broader APT43 designation – another name for Kimsuky.
Our analysis shows that the actor retains access to the original source code of the malware clusters and the ability to modify it. Over time, malware undergoes updates and modifications, sometimes being repurposed or reused by other actors. Although analyzing malware may seem repetitive and time-consuming, understanding how these tools evolve helps us grasp the threat actor’s changing tactics.
Two clusters have overlapping target sectors that span the defense, military, government, medical, machinery, and energy industries. The AppleSeed cluster is shifting its focus to data exfiltration, and GPKI certificate extraction has become a signature capability. Meanwhile, the PebbleDash cluster demonstrates advanced remote control capabilities and an expanding set of targets.
Although AI may offer full automation for some attacks, many groups stick with the tools and strategies they have used for years. Structuring a fully automated attack is not trivial. Despite ongoing changes, we will continue to track advanced threat actors by comprehensively considering malware, initial vectors, targets, post-exploitation activities, and ultimate goals.
JSE Dropper
995a0a49ae4b244928b3f67e2bfd7a6e [별지 제8호서식] 개인정보(열람 정정삭제 처리정지) 요구서(개인정보 보호법 시행규칙).hwp.jse
52f1ff082e981cbdfd1f045c6021c63f 2026년 상반기 국내대학원 석사야간과정 위탁교육생 선발관련 서류.hwpx.jse
9fe43e08c8f446554340f972dac8a68c 2026년 상반기 국내대학원 석사야간과정 위탁교육생 선발관련 서류 (1).hwpx.jse
8e15c4d4f71bdd9dbc48cd2cabc87806 노현정님.pdf.jse
Reger Dropper
65fc9f06de5603e2c1af9b4f288bb22c security_20260126.scr
c19aeaedbbfc4e029f7e9bdface495b9 secu.scr
Pidoc Dropper
8983ffa6da23e0b99ccc58c17b9788c7 대국민서비스관리운영체계_현장점검_증적(초안).pif
AppleSeed (Dropper)
a7f0a18ac87e982d6f32f7a715e12532
f4465403f9693939fe9c439f0ab33610
5c373c2116ab4a615e622f577e22e9be
HappyDoor
d1ec20144c83bba921243e72c517da5e
MemLoad
58ac2f65e335922be3f60e57099dc8a3
f73ba062116ea9f37d072aa41c7f5108 jhsakqvv.dat
httpTroy
7e0825019d0de0c1c4a1673f94043ddb c:\programdata\config.db
httpMalice
08160acf08fccecde7b34090db18b321
94faed9af49c98a89c8acc55e97276c9
HelloDoor
c42ae004badddd3017adadbdd1421e00
VSCode Tunnel installer
9ca5f93a732f404bbb2cee848f5bbda0 xipbkmaw.exe
DWAgent installer
678fb1a87af525c33ba2492552d5c0e2
opedromos1.r-e[.]kr C2 of AppleSeed
morames.r-e[.]kr C2 of AppleSeed
load.ssangyongcne.o-r[.]kr C2 of MemLoad
load.yju.o-r[.]kr C2 of MemLoad
attach.docucloud.o-r[.]kr C2 of MemLoad
load.supershop.o-r[.]kr C2 of MemLoad
load.erasecloud.n-e[.]kr C2 of MemLoad
cms.spaceyou.o-r[.]kr C2 of HappyDoor
erp.spaceme.p-e[.]kr C2 of HappyDoor
file.bigcloud.n-e[.]kr C2 of httpTroy
load.auraria[.]org C2 of httpTroy
female-disorder-beta-metropolitan.trycloudflare[.]com C2 of HelloDoor
hxxps://www.pyrotech.co[.]kr/common/include/tech/default.php C2 of httpMalice
hxxp://newjo-imd[.]com/common/include/library/default.php C2 of httpMalice
hxxps://www.yespp.co[.]kr/common/include/code/out.php VSCode Tunneling using JScript
If you downloaded the JDownloader installer during the compromise window (May 6-7), you are advised to verify the file.
JDownloader is a popular download management application, particularly favored for automated downloads from file-hosting services, video sites, and premium link generators.
The JDownloader website was confirmed to have been compromised on May 6-7, 2026. During that window, the Windows “Download Alternative Installer” links and the Linux shell installer were compromised. Other download options, including macOS, JAR files, Flatpak, Winget, and Snap packages remained safe.
Users that applied updates during that period were not affected. The malicious Windows installers deployed a Python-based remote access Trojan (RAT).
The developers confirmed the breach on May 7, immediately taking the website offline for investigation. After security patches were applied and server configurations hardened, the website was restored on May 8-9 with verified clean installer links. The attack vector was identified as an unpatched CMS security bug that allowed attackers to modify access control lists without authentication.
The developers advised users to verify that their installers have the proper digital signatures from “AppWork GmbH,” which compromised versions lacked.
A full system scan with a trusted anti-malware solution never hurts either.
Malwarebytes blocks the domains contacted by the RAT.
We don’t just report on threats—we remove them
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
If you downloaded the JDownloader installer during the compromise window (May 6-7), you are advised to verify the file.
JDownloader is a popular download management application, particularly favored for automated downloads from file-hosting services, video sites, and premium link generators.
The JDownloader website was confirmed to have been compromised on May 6-7, 2026. During that window, the Windows “Download Alternative Installer” links and the Linux shell installer were compromised. Other download options, including macOS, JAR files, Flatpak, Winget, and Snap packages remained safe.
Users that applied updates during that period were not affected. The malicious Windows installers deployed a Python-based remote access Trojan (RAT).
The developers confirmed the breach on May 7, immediately taking the website offline for investigation. After security patches were applied and server configurations hardened, the website was restored on May 8-9 with verified clean installer links. The attack vector was identified as an unpatched CMS security bug that allowed attackers to modify access control lists without authentication.
The developers advised users to verify that their installers have the proper digital signatures from “AppWork GmbH,” which compromised versions lacked.
A full system scan with a trusted anti-malware solution never hurts either.
Malwarebytes blocks the domains contacted by the RAT.
We don’t just report on threats—we remove them
Cybersecurity risks should never spread beyond a headline. Keep threats off your devices by downloading Malwarebytes today.
Over the past few months, we have conducted an in-depth analysis of specific activity clusters of Kimsuky (aka APT43, Ruby Sleet, Black Banshee, Sparkling Pisces, Velvet Chollima, and Springtail), a prolific Korean-speaking threat actor. Our research revealed notable tactical shifts throughout multiple phases of the group’s latest campaigns.
Kimsuky has continuously introduced new malware variants based on the PebbleDash platform, a tool historically leveraged by the Lazarus Group but appropriated by Kimsuky since at least 2021. Our monitoring indicates various strategic updates to the group’s arsenal, including the use of VSCode Tunneling, Cloudflare Quick Tunnels, DWAgent, large language models (LLMs), and the Rust programming language. This expanding set of tools underscores the group’s ongoing adaptation and evolution.
Specifically, Kimsuky leveraged legitimate VSCode tunneling mechanisms to establish persistence and distributed the open-source DWAgent remote monitoring and management tool for post-exploitation activities. These activities affected various sectors in South Korea, impacting both public and private entities.
This article covers both previously undocumented attacks and a deeper technical analysis of incidents within this campaign that have been reported before — offering new insight beyond what has already been published.
First identified by Kaspersky in 2013, Kimsuky has been active for over 10 years and is considered less technically proficient compared to other Korean-speaking APT groups. The group has targeted a wide range of entities and demonstrated capability in creating tailored spear-phishing emails. The group’s arsenal includes proprietary malware such as PebbleDash, BabyShark, AppleSeed, and RandomQuery, as well as open-source RATs like xRAT, XenoRAT, and TutRAT. This blog post examines the evolving PebbleDash-based malware (referred to as the PebbleDash cluster) and its connections to the AppleSeed-based malware (referred to as the AppleSeed cluster).
The PebbleDash and AppleSeed clusters are considered the most technically advanced in Kimsuky’s toolset. Since at least 2019, these clusters have masqueraded as legitimate documents and application installers, manifesting as JSE droppers or executables with .EXE, .SCR and .PIF extensions. Both are particularly adept at establishing backdoors and stealing information, and ongoing development of their variants has been observed. They even occasionally utilize stolen legitimate certificates from South Korean organizations to avoid detection.
Timeline of the AppleSeed and PebbleDash malware families
AppleSeed and PebbleDash have primarily targeted the public and private sectors in South Korea. The PebbleDash cluster has shown a particular interest in the medical, military and defense industries worldwide. The PebbleDash cluster compromised Brazilian and South Korean defense organizations throughout the past several years, as well as a German defense firm. In 2024, the South Korean government released a security advisory regarding the AppleSeed cluster, detailing how the malware was distributed by replacing a security software installer required to access a construction entity’s website.
Kimsuky meticulously crafts and delivers spear-phishing emails to its targets in an attempt to entice them into opening attachments. According to recent research, the group also occasionally approaches targets by contacting them via messengers. In all cases, the initial contact leads to the delivery of a malicious attachment disguised as a document. These attachments often consist of compressed files containing droppers in formats such as .JSE, .EXE, .PIF, or .SCR. The filenames are consistent with the message content and are meant to convince the recipient to open the attachment. The malicious files are often disguised as product quotations, job offers, information guides, surveys, government documents, and personal photos.
Here are some recently discovered examples:
| Number | Filename | Filename (translated to English) | Detection date | MD5 | Malware deployed |
| 1 | [별지 제8호서식] 개인정보(열람 정정삭제 처리정지) 요구서(개인정보 보호법 시행규칙).hwp.jse | Appendix Form No. 8 – Request for Access, Correction, Deletion, and Suspension of Processing of Personal Information (PIPA Enforcement Rules).hwp.jse | August 28, 2025 | 995a0a49ae4b244928b3f67e2bfd7a6e | HelloDoor |
| 2 | 2026년 상반기 국내대학원 석사야간과정 위탁교육생 선발관련 서류.hwpx.jse | Documents for the Selection of Commissioned Students for Domestic Graduate School Master’s Evening Programs (H1 2026).hwpx.jse | December 14, 2025 | 52f1ff082e981cbdfd1f045c6021c63f | httpMalice |
| 3 | security_20260126.scr | – | January 26, 2026 | 65fc9f06de5603e2c1af9b4f288bb22c | Reger Dropper, MemLoad, httpTroy |
| 4 | 노현정님.pdf.jse | Ms. Noh Hyun-jung.pdf.jse | January 28, 2026 | 8e15c4d4f71bdd9dbc48cd2cabc87806 | AppleSeed chain |
| 5 | 대국민서비스관리운영체계현장점검증적(초안).pif | On-site Inspection Evidence for the Public Service Management System (Draft).pif | February 5, 2026 | 8983ffa6da23e0b99ccc58c17b9788c7 | Pidoc Dropper, HappyDoor |
JSE droppers contain a minimum of two Base64-encoded blobs: one serving as a benign lure file and one or more containing malicious code. Additional blobs may exist within the dropper, but they are unused. The two blobs are decoded using JScript and stored in an arbitrary location on disk, such as C:\ProgramData, with the malicious filenames randomly generated according to the scheme [random]{7}.[random]{4}. The lure file is opened immediately. The malicious payload leverages powershell.exe -windowstyle hidden certutil -decode [src path] [dst path] for the second Base64 decoding before execution. Ultimately, the malicious payload is executed via command-line instructions such as regsvr32.exe /s [file path] or rundll32.exe [file path] [export function].
Reger Dropper (.SCR) and Pidoc Dropper (.PIF) also contain benign lure files and malicious payloads that, in both cases, are encrypted using XOR operations. Specifically, Reger Dropper employs a hard-coded key #RsfsetraW#@EsfesgsgAJOPj4eml;, while Pidoc Dropper utilizes single-byte XOR with 0xFF to decrypt the internal data for execution. Pidoc Dropper is fully obfuscated using dummy data and encrypted strings. Both droppers deploy files in specific directories such as %temp% or C:\ProgramData before executing the malware using regsvr32.exe.
In addition to these droppers, Kimsuky employed a variety of executable droppers, including those crafted in Go or packaged with Inno Setup.
In this section, we describe several malware families recently dropped by the droppers discussed above.
Written in Rust, a programming language rarely used by Kimsuky, HelloDoor is a DLL-based backdoor first identified in August 2025. It is deployed via a malicious JSE dropper. Since it has limited capabilities and a simplistic communication mechanism, the backdoor is most probably in the early stages of development. Nevertheless, it is noteworthy that HelloDoor employs a C2 server hosted through TryCloudflare, a temporary tunneling service provided by Cloudflare. This service allows users to expose a local web service to the internet with no setup or account, making the infrastructure behind it difficult to trace.
HelloDoor establishes persistence upon execution by registering itself to the HKCU\Software\Microsoft\Windows\CurrentVersion\Run key with the value name tdll and the command regsvr32.exe /s [current file path].
The implant communicates with the C2 server (hxxp://female-disorder-beta-metropolitan.trycloudflare[.]com/index.php) over the HTTP protocol. Depending on whether the process is executing with an elevated token, it binds to a specific local port: 5555 if the token is elevated, or 5554 if not. Before initiating communication, it generates a unique identifier by collecting device information, such as the MAC address, computer name, and the string “windows”, then computes a hash value from this information.
The malware then constructs a query string in the format aaaaaaaaaa=2&bbbbbbbbbb=[the unique identifier]&cccccccccc=1, which is a traditional format used across the PebbleDash cluster. Subsequent server responses are Base64-decoded and then decrypted using RC4 with the key fwr3errsettwererfs. The decrypted content contains command strings. Possible commands are:
| Command | Description |
| “mcd” | Set the current directory |
| “msleep” | Sleep for the provided time |
| “install” | Register the regsvr32.exe /s [the provided file path] command to the HKCU\Software\Microsoft\Windows\CurrentVersion\Run autorun registry using the install value name |
| [command] | Execute the provided command using chcp 65001 > nul & cmd /U /C [command] |
Though interesting, it is no longer surprising that we found comments in the code that appear to have been generated by an LLM service rather than a human developer. This is based on traces that include emojis used for logging debugging messages.
✅ Port is now listening (no accepting) ❌ Port is already in use 🔍 regsvr32.exe detected as parent. Attempting to terminate...
This is a common trait of LLM services that provides users with better visibility. We previously observed similar comments in the PowerShell-based stealer suite used by BlueNoroff. HelloDoor’s simple structure and the fact that no other Rust-based malware from the group has been discovered yet support our claim.
Even though the code is believed to have been developed using an LLM service, we still found some typos and grammatical errors, such as:
It is likely that the flawed comments were added manually before or after AI was used.
The latest PebbleDash-based backdoor, httpMalice, emerged no later than December 2025 and is deployed by the JSE Dropper. Although we found limited direct connections to both the AppleSeed and PebbleDash clusters, the malware is closer to PebbleDash. The following shared characteristics have been identified:
S-1-12-12288 SID, indicating a high integrity level – a feature also observed in PebbleDash and httpTroy.m= parameter in C2 communication.Our analysis revealed two distinct versions of httpMalice based on their C2 communications: version 1.9 communicates over HTTP and version 1.8 uses Dropbox. The latter, the older variant, leverages the Dropbox API by utilizing pre-defined application credentials. Unlike its predecessor, the HTTP variant employs HTTP/HTTPS protocols to interact with its C2 server and maintains persistent access to the victim device through a Windows service named CacheDB. This mirrors tactics observed in similar threats, such as httpSpy.
The more recent variant gathers critical information from the compromised system, such as the current directory path, volume serial numbers, user privileges, username, local IP address, and the name and size of the currently executed httpMalice DLL file. It then combines the root drive’s volume serial number with the user’s access token privilege level to create a unique identifier for each infected system, formatted as [volume serial]{8}_[elevation status].
| Value of elevation status | Description |
| 0 | Running under the SYSTEM account with an elevated token |
| 1 | Running under an elevated administrator account |
| 2 | Running without elevation |
Depending on the token privilege, the backdoor then establishes persistence by either creating a service or registering itself to autostart at user logon. If the token is elevated, a service named CacheDB is created that executes the command cmd.exe /c “rundll32.exe [current DLL path], load”. The service’s display name is set to Administrator, and its description is defined as CacheDB Service. If the token is not elevated, the backdoor registers the same command under the registry key HKCU\Software\Microsoft\Windows\CurrentVersion\Run with the value name Everything 1.9a-[filesize]. The older version used Everything 1.8a-[filesize] as a value name.
The latest version can execute a combination of Windows commands by default to perform host profiling, while the older version fetches the command set from Dropbox. In httpMalice, commands are mostly executed using the format cmd.exe /c chcp 949 [command] > [temporary filename], which redirects the output to separate files, with the consistent prefix 2Ato6478s added to their names. The chcp 949 command changes the code page to 949, indicating that the malware targets users of the Korean language (EUC-KR charset).
Windows commands used to gather system details
httpMalice transmits the result of host profiling to its C2 server as a URL parameter, using the POST method over the HTTP/HTTPS protocol, with the header x-www-form-urlencoded. The URL includes two or three parameters: operation mode, unique identifier (referred to as UID), and data. The operation mode, or parameter m, supports the following values:
| Value | Description |
| 1 | Send the session identifier (parameter s) along with the current state (parameter a) |
| 2 | Request command |
| 3 | Send result after executing the command (parameter d) |
| 8 | Request directory to be archived and sent |
| 9 | Send the archived directory |
| 10 | Send a message like “.cmd” or “.tmp” (parameter d) |
| 11 | Send ping |
| 12 | Send the captured screenshot (parameter d) |
| 13 | Send the infected device information (parameter d) |
As shown in the table above, the mode is set to 13 at the host profiling stage. The UID is formatted as [volume serial]{8}_[elevation status], and the data contains the ChaCha20-encrypted and Base64-encoded output of the command set stored in the temporary file. The resulting URL format is: m=13&u=[volume serial]{8}_[elevation status]&d=[Chacha20 encrypted + Base64-encoded data to be sent].
The key and nonce used for ChaCha20 encryption are derived from the pointer address of the buffer, resulting in nearly randomized keys. To ensure proper decryption on the attacker side, the nonce and key values are appended after the encrypted data, and the combined blob is then Base64-encoded. The counter is initialized to 0. The following figure illustrates how the encrypted data is structured after performing Base64 decoding.
Structure of the ChaCha20-encrypted data blob
After sending the host profiling data, the backdoor continuously transmits a screen capture with mode 12 and a ping message with mode 11. Finally, it sends a session identifier, which is a combination of the current username and local IP address separated by an ‘@’ symbol. In this case, the mode is set to 1 and the a parameter (current state) is set to 0, indicating that the C2 operation has been activated. The following table provides other possible values of the a parameter:
| Value | Description |
| 0 | httpMalice has been activated |
| 1 | httpMalice has been inactivated (upon command 9) |
| 2 | httpMalice has been removed (upon command 8) |
The whole process from sending the host profile to the backdoor activation repeats every two minutes until the C2 server returns a “success!” message.
C2 communication sequence of httpMalice
When the backdoor receives the message from the C2 server, it creates two threads dedicated to processing commands and sending the current state, including the session identifier. The first thread receives a command from the C2 server. It requests a command by sending mode 2 and, if successful, immediately sends mode 10 along with the string “.cmd” in the d parameter.
The commands supported by httpMalice are as follows:
| Command | Description |
| 0 | Do nothing |
| 1 | Execute the command with EUC-KR encoding |
| 2 | Download and extract the file to the infected device |
| 3 | Upload a directory to the C2 server after it has been archived |
| 5 | Get the current directory |
| 6 | Set the current directory |
| 7 | Execute the command without setting a EUC-KR character set |
| 8 | Remove its persistence traces and exit the process |
| 9 | Hibernate |
| 10 | Execute the command using the provided session ID |
| 12 | Capture the screen |
| 13 | Load the downloaded payload into memory |
Since early 2025, we have observed several versions of MemLoad; specifically, MemLoad V2 emerged in March, and V3 appeared by September. The payload that began being deployed through the Reger Dropper this year has been identified as an updated variant of MemLoad, slightly modified from the V3 version (referred to internally as MemLoader.dll).
Kimsuky leverages MemLoad to evade detection of its final backdoor and to carefully assess the value of targeted systems through anti-VM checks and reconnaissance. Upon installation, it requests an additional payload from the C2 server, executing it reflectively in memory if deemed suitable. Notably, all versions of MemLoad V2 and later use the same RC4 key.
Below are the key operations of MemLoad:
C:\Windows\system32 directory. If successful, the ID starts with ‘A-‘ (indicating administrative privileges); otherwise, it starts with ‘U-‘.ChromeCheck, and the command
schtasks /create /tn <task name> /tr "regsvr32 /s <current file path>" /sc minute /mo 1 /rl highest /f is executed. Otherwise, the task is named EdgeCheck, and the command
schtasks /create /tn <task name> /tr "regsvr32 /s <current file path>" /sc minute /mo 1 /f is executed.Authorization: Bearer {ID} or X-Browser-Validation: {ID} for authentication. The ID is set to the previously generated ID value.#RsfsetraW#@EsfesgsgAJOPj4eml;. The decrypted payload is then reflectively loaded into memory, and its hello export function is invoked.The payload downloaded and executed by MemLoad is identified as the httpTroy backdoor. This backdoor serves as the primary role for long-term access and data exfiltration. Similar to MemLoad, it employs stealth techniques by creating a flag file and writing eight random bytes to it. However, in this case the file is created at [current file path]:HUI in the ADS (Alternative Data Stream) area. The backdoor then checks its privileges to determine if it is elevated and assigns an ID value in the format A-[random-8-chars] or U-[random-8-chars].
Since Gen Digital covers httpTroy’s features and functionality in detail elsewhere, we will not provide a thorough explanation here to avoid redundancy. Instead, we will simply note that it communicates with the C2 server at hxxps://file.bigcloud.n-e[.]kr/index.php.
AppleSeed first appeared in 2019 and reached version 3.0. However, we now only see version 2.1. It originally consisted of two components: a dropper and the main AppleSeed. Since 2022, the updated AppleSeed chain has involved two droppers, an additional component referred to as the installer, and the main payload. It is mostly delivered through JSE Dropper.
Updated AppleSeed infection chain
There are two versions of the main AppleSeed: Dropper and Spy. The Dropper variant is responsible for downloading additional malware and executing commands received from its C2 server, while the Spy version gathers sensitive information such as documents, screenshots, keystrokes, and lists of USB drives. A notable change in version 2.1 is the inclusion, since 2022, of collecting the C:\GPKI directory – functionality that is also implemented in Troll Stealer. This directory contains a digital certificate used by the South Korean government to securely authenticate public officials and government systems.
HappyDoor, an AppleSeed-based backdoor malware disclosed by AhnLab in 2024, is less visible than AppleSeed. HappyDoor shares several features with AppleSeed, including the same string obfuscation algorithm, the data types it collects, and the use of RSA encryption. Given these similarities, we assess with medium confidence that HappyDoor is an advanced variant evolved from AppleSeed.
We observed interesting post-exploitation activities involving VSCode and DWAgent. All of the observed VSCode droppers used the same lure files as the PebbleDash malware cluster. While we are unsure of the exact reason for this strategy, we suspect that the actor prepared both PebbleDash and VSCode droppers in anticipation of the PebbleDash infection chain being detected by security products because of its backdoor capabilities. In contrast, the use of VSCode is designed to have fewer detection points.
Since last year, Kimsuky has been leveraging the legitimate Visual Studio Code Remote Tunneling feature to establish covert remote access to the victim’s device, bypassing detection designed for traditional malware-based C2 channels (first described by Darktrace researchers). In these attacks, instead of dropping malware, the JSE dropper downloads a legitimate Visual Studio Code (VSCode) CLI onto the infected device. The script establishes persistence by creating a tunnel via the application, with the tunnel name “bizeugene”, using the command below.
The Remote Tunneling feature in VSCode supports establishing a tunnel using either a Microsoft or GitHub account. When the code tunnel command is executed, the CLI initiates an authentication flow and returns a login URL along with a device code. The user must then navigate to the URL, enter the device code, and authenticate with their account. Once authentication is successful, the tunnel is created and the CLI outputs a URL for tunneling that enables browser-based access to the remote host.
The GitHub authentication method is selected in this instance because GitHub is configured as the default provider in non-interactive execution contexts. By using echo |, the script injects a \r\n (Carriage Return and Line Feed) into the standard input stream, effectively confirming the default prompt selection without manual interaction. As a result, the CLI automatically initiates the GitHub authentication flow. Next, all CLI output that includes a login URL and a device code is saved to out.txt.
Out.txt content
The JScript code in the JSE dropper monitors the out.txt file for a URL that begins with hxxps://vscode[.]dev/tunnel. This URL contains the full address of the established tunnel. Once detected, the file content containing the URL and the device code is sent to a compromised legitimate South Korean website (hxxps://www.yespp.co[.]kr/common/include/code/out[.]php) using the HTTP POST method. The request contains the file contents in the application/x-www-form-urlencoded header data formatted as out=URLencoded{result of the command}&token=URLencoded{"bizeugene"}. After authentication is complete, the attacker can access the compromised host externally through a web browser by authenticating with their own GitHub account.
While searching our telemetry for artifacts related to a different infection, we identified a new VSCode tunnel installer written in Go. A previous version of this installer was implemented using JScript and was limited to secure channels because of its reliance on a specific tunnel name. The new variant, named vscode_payload by the developer based on the embedded Go path, is fully operational and supports every tunnel on each targeted device. It includes features that are nearly identical to those of the previous version, such as downloading, unarchiving, and executing the VSCode CLI.
| Number | Installer type | VSCode version | Download source |
| 1 | Written in JScript | VSCode CLI 1.106.3 | hxxps://vscode.download.prss.microsoft[.]com/dbazure/download/stable/bf9252a2fb45be6893dd8870c0bf37e2e1766d61/vscode_cli_win32_x64_cli[.]zip |
| 2 | Written in Go | VSCode CLI 1.106.2 | hxxps://vscode.download.prss.microsoft[.]com/dbazure/download/stable/1e3c50d64110be466c0b4a45222e81d2c9352888/vscode_cli_win32_x64_cli[.]zip |
After the VSCode CLI file has been successfully downloaded, it is unzipped into the C:\Users\Public directory, and the extracted code.exe is executed with the tunnel command.
This is how the installer works:
code.exe tunnel.0x1B 0x5B 0x42 (Down Arrow) and 0x0A (Enter) escape sequence to the pseudo-terminal, which enables tunnel creation via a GitHub account.0x0A escape sequence to the pseudo-terminal to use the current machine name as the identifier.The following figure illustrates the sequence for creating a tunnel using the VSCode CLI. Red boxes highlight the strings that the installer searches for. Yellow boxes indicate standard input operations sent from the installer using escape sequences. Sky blue boxes represent the values that are necessary to create the tunnel on the attacker’s side. (The “Microsoft Account” string in the second step is not shown in this figure because the second “GitHub Account” was already selected during the process.)
Creating a tunnel using VSCode CLI
Once the process is complete, the attacker can access the targeted host through the tunnel on their remote machine using their GitHub account via a browser or VSCode. The targeted device then begins communicating with Microsoft-owned servers without the user realizing that the communication is from an attacker.
An interesting feature of this variant is that it sends debugging messages and necessary values to a Slack channel via a WebHook. Upon execution, it sends "+++ I am started +++", as well as a heartbeat message "~~~ I am alive ~~~" approximately every second during tunneling authentication.
DWAgent is a remote administration tool that is frequently exploited by threat actors, including ransomware and APT groups, to easily access compromised endpoints with minimal risk of detection. Kimsuky is one of the threat actors that uses this tool in its operations.
We observed that the group delivered DWAgent in at least two ways. The first involved delivering a compressed file containing DWAgent, along with separate commands, to a host infected with httpMalice for installation. The second method involved creating a separate installer.
This installer is very similar to the Reger Dropper. It uses the same RC4 key and has a similar code structure. It includes an archived binary and a legitimate unrar.exe binary, both encrypted with RC4. When executed, the installer decrypts the archived binary and saves it as 1.zip in the C:\ProgramData directory. It also creates an unrar.exe file in the same location using the decrypted unrar.exe binary. The dropper then uses the command C:\programdata\unrar.exe x C:\programdata\1.zip C:\programdata\ to extract the contents of the ZIP file. Finally, it executes the commands necessary to install DWService as a service on the target host:
The compressed file contains a pre-packaged, ready-to-use DWAgent, as well as a predefined config file. The actor deployed the agent with a config.json file linked to their own account to covertly control the device. As a result, the remote session is immediately activated by the above command, granting the attacker control.
The predefined config file is as follows. Note that the servers are legitimate DWAgent relay servers.
{
"enabled": true,
"key": "kDRNGmWGTMpjQmREgQzU",
"listen_port": 7950,
"nodes": [
{
"id": "ND896147",
"port": "443",
"server": "node896147.dwservice[.]net"
},
{
"id": "ND828765",
"port": "443",
"server": "node828765.dwservice[.]net"
},
{
"id": "ND484265",
"port": "443",
"server": "node484265.dwservice[.]net"
}
],
"password": "eJwrynEqD0r294twTXLKCHWqDPLPCql0Kg/JDqpIdk4HAKYMCso=",
"url_primary": "hxxps://www.dwservice[.]net/"
}
For years, Kimsuky has relied heavily on the South Korea-based free domain hosting service 내도메인[.]한국 (pronounced as “naedomain[.]hankook) to mimic legitimate sites with domains like .p-e.kr, .o-r.kr, .n-e.kr, .r-e.kr, and .kro.kr. This service has been utilized to create C2 servers for PebbleDash and AppleSeed clusters, and the background infrastructures have been mostly resolved to the virtual private servers belonging to InterServer. It has also been noted that many other malicious actors have exploited this free domain hosting service, so it alone cannot be considered proof of a connection to Kimsuky.
The actor also occasionally exploits South Korean websites as C2 servers to evade network-IoC-based detection and increase the success rate of attacks. Furthermore, they actively leverage tunneling services such as Cloudflare Quick Tunnels, VSCode Tunneling, and Ngrok to hide their infrastructure. These traits are mostly observed across the PebbleDash cluster.
We identified multiple infection logs uploaded to the Dropbox storage used for httpMalice’s C2 server. They were analyzed as having been stolen from infected systems across various organizations or individuals in South Korea. Notably, each victim’s folder contained a user.txt file with detailed information such as target details, the presence of something named “http” (possibly a backdoor, such as httpTroy or httpMalice), DWAgent existence, and relationships between infected devices and targets. While we could not verify the exact creation process of these files, they were likely created manually by attackers to manage victims using Korean words.
Below you can see an example of this type of file content. In this context, “장악” means “take over” and “있음” means “exists”.
[Target's name] [Description] [Infection date] 장악, http 있음, DWService 있음.
While both clusters have mainly focused on targeting the private and public sectors in South Korea, the AppleSeed malware cluster shows more interest in government entities. The PebbleDash cluster has also shown particular interest in the defense sector worldwide.
Over the past few years, we have observed two clusters using overlapping distribution methods – JSE, EXE, SCR, and PIF droppers. The targets are also increasingly aligning. Furthermore, we noted that several samples from both malware clusters were signed with the same stolen certificate and used identical mutex patterns. These findings suggest that a single actor is likely controlling both clusters and has the capability to modify code as needed. This concept was also described in another research paper at the Virus Bulletin conference.
Since its emergence, AppleSeed has been linked to Kimsuky operations, with each variant showing ties to the group. Since 2021, PebbleDash has been found exclusively in Kimsuky attacks. Based on our analysis of targets, infrastructure, and malware characteristics, we assess with medium-high confidence that attacks associated with these malware families are conducted by Kimsuky-affiliated clusters.
These two clusters share technical links to the threat actor known as Ruby Sleet, one of the names Microsoft uses for Kimsuky activity. In previous reports, Mandiant also referred to these clusters as Cerium, but now they appear to consider them part of the broader APT43 designation – another name for Kimsuky.
Our analysis shows that the actor retains access to the original source code of the malware clusters and the ability to modify it. Over time, malware undergoes updates and modifications, sometimes being repurposed or reused by other actors. Although analyzing malware may seem repetitive and time-consuming, understanding how these tools evolve helps us grasp the threat actor’s changing tactics.
Two clusters have overlapping target sectors that span the defense, military, government, medical, machinery, and energy industries. The AppleSeed cluster is shifting its focus to data exfiltration, and GPKI certificate extraction has become a signature capability. Meanwhile, the PebbleDash cluster demonstrates advanced remote control capabilities and an expanding set of targets.
Although AI may offer full automation for some attacks, many groups stick with the tools and strategies they have used for years. Structuring a fully automated attack is not trivial. Despite ongoing changes, we will continue to track advanced threat actors by comprehensively considering malware, initial vectors, targets, post-exploitation activities, and ultimate goals.
JSE Dropper
995a0a49ae4b244928b3f67e2bfd7a6e [별지 제8호서식] 개인정보(열람 정정삭제 처리정지) 요구서(개인정보 보호법 시행규칙).hwp.jse
52f1ff082e981cbdfd1f045c6021c63f 2026년 상반기 국내대학원 석사야간과정 위탁교육생 선발관련 서류.hwpx.jse
9fe43e08c8f446554340f972dac8a68c 2026년 상반기 국내대학원 석사야간과정 위탁교육생 선발관련 서류 (1).hwpx.jse
8e15c4d4f71bdd9dbc48cd2cabc87806 노현정님.pdf.jse
Reger Dropper
65fc9f06de5603e2c1af9b4f288bb22c security_20260126.scr
c19aeaedbbfc4e029f7e9bdface495b9 secu.scr
Pidoc Dropper
8983ffa6da23e0b99ccc58c17b9788c7 대국민서비스관리운영체계_현장점검_증적(초안).pif
AppleSeed (Dropper)
a7f0a18ac87e982d6f32f7a715e12532
f4465403f9693939fe9c439f0ab33610
5c373c2116ab4a615e622f577e22e9be
HappyDoor
d1ec20144c83bba921243e72c517da5e
MemLoad
58ac2f65e335922be3f60e57099dc8a3
f73ba062116ea9f37d072aa41c7f5108 jhsakqvv.dat
httpTroy
7e0825019d0de0c1c4a1673f94043ddb c:\programdata\config.db
httpMalice
08160acf08fccecde7b34090db18b321
94faed9af49c98a89c8acc55e97276c9
HelloDoor
c42ae004badddd3017adadbdd1421e00
VSCode Tunnel installer
9ca5f93a732f404bbb2cee848f5bbda0 xipbkmaw.exe
DWAgent installer
678fb1a87af525c33ba2492552d5c0e2
opedromos1.r-e[.]kr C2 of AppleSeed
morames.r-e[.]kr C2 of AppleSeed
load.ssangyongcne.o-r[.]kr C2 of MemLoad
load.yju.o-r[.]kr C2 of MemLoad
attach.docucloud.o-r[.]kr C2 of MemLoad
load.supershop.o-r[.]kr C2 of MemLoad
load.erasecloud.n-e[.]kr C2 of MemLoad
cms.spaceyou.o-r[.]kr C2 of HappyDoor
erp.spaceme.p-e[.]kr C2 of HappyDoor
file.bigcloud.n-e[.]kr C2 of httpTroy
load.auraria[.]org C2 of httpTroy
female-disorder-beta-metropolitan.trycloudflare[.]com C2 of HelloDoor
hxxps://www.pyrotech.co[.]kr/common/include/tech/default.php C2 of httpMalice
hxxp://newjo-imd[.]com/common/include/library/default.php C2 of httpMalice
hxxps://www.yespp.co[.]kr/common/include/code/out.php VSCode Tunneling using JScript
Our experts have discovered a large-scale supply chain attack via DAEMON Tools – software for emulating optical drives. The attackers managed to inject malicious code into the software installers, and all trojanized executable files are signed with a valid digital signature of AVB Disc Soft – the developer of DAEMON Tools. The malicious version of the program has been circulating since April 8, 2026. At the time of writing, the attack is still ongoing. Researchers at Kaspersky believe this is a targeted attack.
After the Trojanized software is installed on the victim’s computer, a malicious file is launched every time the system starts up – sending a request to a command-and-control server. In response, the server may send a command to download and execute additional malicious payloads.
First, the attackers deploy an information gatherer that collects the MAC address, hostname, DNS domain name, lists of running processes and installed software, and language settings. The malware then sends this information to the command-and-control server.
In some cases, in response to the collected information, the command server sends a minimalistic backdoor to the victim’s machine. It’s capable of downloading additional malicious payloads, executing shell commands, and running shellcode modules in memory.
The backdoor can be used to deploy a more sophisticated implant dubbed as QUIC RAT. It supports multiple communication protocols with the command-and-control server, and is capable of injecting malicious payloads into the notepad.exe and conhost.exe processes.
More detailed technical information, along with indicators of compromise, can be found in the experts’ article on the Securelist blog.
Since early April, several thousand attempts to install additional malicious payloads via infected DAEMON Tools software have been detected. Most of the infected devices belonged to home users, but approximately 10% of installation attempts were detected on systems running in organizations. Geographically, the victims were spread across around a hundred different countries and territories. Most victims were located in Russia, Brazil, Turkey, Spain, Germany, France, Italy, and China.
Most often, the attack was limited to installing an information collector. The backdoor infected only a dozen machines in government, scientific, and manufacturing organizations, as well as in retail businesses in Russia, Belarus, and Thailand.
The malicious code was detected in DAEMON Tools versions ranging from 12.5.0.2421 to 12.5.0.2434. The attackers compromised the files DTHelper.exe, DiscSoftBusServiceLite.exe, and DTShellHlp.exe, which are installed in the main DAEMON Tools directory.
Updated on March 6: Following disclosure, the vendor acknowledged the issue and published a new version of the software to address it. The updated DAEMON Tools version 12.6.0.2445 no longer shows the malicious behavior described in this article.
If DAEMON Tools software is used on your computer (or elsewhere in your organization), our experts recommend thoroughly checking the computers on which it is installed for any unusual activity starting from April 8.
In addition, we recommend using reliable security solutions on all home and corporate computers used to access the internet. Our solutions successfully protect users from all malware used in the supply chain attack via DAEMON Tools.
