If you’re a user—owner?—of this cryptocurrency, this is important:
On May 29, the security researcher Taylor Hornby found a critical vulnerability in Zcash Orchard privacy pool using Claude Opus 4.8. The Zcash team hired Hornby specifically to look for this kind of issue. He found one fast enough to be embarrassing.
The Orchard pool is the newest and most advanced shielded transaction system in the cryptocurrency Zcash. Introduced in 2022, it allows users to send and receive ZEC while keeping transaction details private. It uses zero-knowledge proofs to validate transactions without revealing amounts or participants. The bug: a specific check that was supposed to validate transaction inputs wasn’t actually enforcing the rules it appeared to enforce. An attacker could have exploited the flaw to feed false inputs into that check and generate ZEC from nothing, with the zero-knowledge proof system blessing the fraudulent transaction as valid.
It’s fixed; that’s the good news. The bad news is that there’s no way of knowing if anyone exploited the vulnerability to steal money. And this fragility is the fundamental problem that makes blockchain such a bad idea.
Those losses stem from 22,364 AI-related complaints. And these figures represent only the reported losses, which may well be the proverbial tip of the iceberg.
The main drivers behind the rise in AI-powered scams are voice cloning, deepfake images and videos, and AI‑generated scripts. These tools have supercharged classic fraud schemes such as romance scams, kidnapping and extortion calls, fake influencers, and government impersonation.
Michael Machtinger, deputy assistant director of the FBI Cyber Division, told the Wall Street Journal:
“AI-created fraudulent communications can look very official and very legitimate to even the most trained individuals.”
The FBI and financial institutions recommend verifying identities via official contact channels. One of their biggest concerns is government impersonation scams, which have evolved from crude IRS gift‑card phone calls into sophisticated, multi‑channel operations that combine spoofed caller ID, stolen agency logos, and AI‑generated audio and video of public officials.
This report, and others like it, shows how AI is being weaponized to automate research on victims, generate convincing scripts, and create highly believable deepfake personas at scale.
AI is also increasingly used in business email compromise (BEC), romance scams, and impersonation fraud. In BEC cases involving AI, losses have already reached tens of millions of dollars for businesses alone.
For a broader look at why AI is simultaneously fueling scams like these and becoming indispensable to defending against them, see my article AI: Threat, tool, or both?
It explains how both defenders and criminals use AI to find vulnerabilities, and why security vendors increasingly rely on AI to process vast amounts of telemetry, detect anomalies, and keep pace with threats that “no longer move at human speed.”
How to stay safe
Consumer protection agencies have documented a growing list of the ways scammers are using AI to try to rip people off. The main problem is that we can no longer take it at face value that the person we’re talking to is who they claim to be.
Government agencies and financial institutions recommend that you:
Be skeptical of urgent payment demands, especially those involving cryptocurrency or gift cards
Limit the amount of voice and video content you share publicly, as it can be reused by scammers
Report incidents quickly to your bank(s) and IC3.gov
Pro tip: Malwarebytes Scam Guard can help you determine whether a message is a scam and guide you through the next steps.
Something feel off? Check it before you click.
Malwarebytes Scam Guard helps you analyze suspicious links, texts, and screenshots instantly.
In April, Anthropic initated Project Glasswing. The idea was to let companies use their new model to find and fix vulnerabilities in their own software. It was a fantastic PR move, and so many press outlets have uncritically parroted Anthropic’s claims that it’s now common wisdom that Mythos is better at finding software vulnerabilities than other models. Which is just nottrue.
In any case, Anthropic has published a Project Glasswing status report. It’s finding a lot of vulnerabilities in software—yay! Some of them are even dangerous. But almost none of them has been patched. It’s weird. There’s something fishy about the data that I don’t understand. That Anthropic refuses to release details—that it just says “trust us”—is a big problem here.
Public attitudes toward Artificial Intelligence (AI) are changing, and we wanted to understand why.
A recent Pew Research survey found that about half of adults say the increased use of AI in daily life makes them more concerned than excited, and that concern has grown over the last few years. People tend to worry most about long‑term social effects (jobs, creativity, relationships, misinformation), even while many do use AI tools and see some practical benefits, particularly for data analysis and routine tasks.
Data from an older UK survey already showed something similar. Awareness of highly visible AI technologies, such as driverless cars and facial recognition is high, but awareness of AI in welfare assessments, loan decisions, or care services is much lower. Concern about many of these use cases has risen since 2022. In other words, people feel AI is everywhere, but don’t always understand where or how it’s being used, and that makes people cautious.
The concern is usually less about science‑fiction extinction scenarios and more about social and economic harm. People worry about their jobs disappearing, a loss of creativity, the spread of disinformation, and increased surveillance, more than about killer robot scenarios.
Research into public attitudes towards AI repeatedly finds that people hold conflicting views, shaped by narratives of admiration and hype on one side and threat and dystopia on the other.
They see genuine benefits in the technology, but are increasingly wary of how companies, governments, and criminals might use it. Basically, people aren’t scared of AI itself, but about who’s using it and for what purpose.
Cybersecurity
AI in cybersecurity is a special case. When asked in which field of AI research they would invest an unlimited amount of money, people chose the fields of medicine and cybersecurity.
People increasingly recognize that AI is now a tool used by both defenders and cybercriminals. Few would feel comfortable with defenders refusing to use AI while attackers continue to adopt it.
Security products use machine learning to process huge volumes of data, detect unusual behavior, prioritize alerts, and identify threats faster than human analysts could alone.
At the same time, cybercriminals are using AI to create more convincing phishing emails, clone voices, generate fake images and videos, automate research on victims, and develop malware that can evade traditional detection techniques.
While studies consistently show that cybersecurity is one of the AI applications people worry about most, they also see that AI is increasingly necessary to keep pace with modern threats. A 2025 study focusing on AI in cybersecurity found that the public widely recognizes the technical benefits of AI‑driven defenses (speed, scale, accuracy), while remaining concerned about privacy, bias, and job displacement in security operations.
That is why the AI debate in cybersecurity feels different from the debate in many other fields. People may be uneasy about AI, but they also understand that the threat landscape no longer moves at human speed. Attackers already use automation, scale, and increasingly AI‑assisted workflows, so defensive teams that refuse to adapt would simply be slower and less effective.
Our mission at Malwarebytes is twofold: reduce the risks created by AI, and use AI to prevent, detect, and respond to threats. We’ve been using machine learning in our security products for nearly two decades, developing proprietary detection systems that help identify malicious code and suspicious behavior at a scale and speed that would be impossible manually.
Coming soon: How AI is changing trust online
Malwarebytes recently surveyed 1,500 adults across the US, UK, Austria, Germany, and Switzerland about their experiences with AI. The findings reveal a growing uncertainty about what people can trust online, alongside increasing concern about scams, impersonation, and AI-generated deception.
Stay tuned for the full Malwarebytes report on how AI is reshaping trust, identity, and scams.
Use AI safely
If you use AI in a security context, keep your data hygiene strict. Don’t paste passwords, customer data, or sensitive incident details into public AI tools. Treat AI-generated outputs as untrusted until verified, especially when they touch code, logs, indicators, or policy decisions.
AI can be useful for summarizing information, indentifying patterns, and producing first drafts, but keep a human in the loop for anything that affects access, containment, legal decisions, or public communications. Where possible, prefer enterprise or local deployments with logging, access control, and clear data-retention rules.
Also remember that AI can hallucinate confidently. In security work, that means every output needs validation against logs, documentation, source code, or other primary evidence before you act on it.
Something feel off? Check it before you click.
Malwarebytes Scam Guard helps you analyze suspicious links, texts, and screenshots instantly.
Hackers are convincing Meta’s AI support chatbot to let them take over other peoples’ accounts:
A video posted on X showed the step-by-step process to hack someone’s Instagram account. The hacker allegedly used a VPN to spoof the targets’ presumed location to avoid triggering Instagram’s automated account protections. Then, the hacker opened a chat with Meta AI Support Assistant and asked the bot to add a new email address to the target’s account. The chatbot can be seen sending a verification code to the email address provided by the hacker; the hacker then shares the verification code with the chatbot, which prompts the chatbot to show a button to “Reset Password.” The hacker enters a new password and takes over the victim’s account.
[…]
On Monday, Instagram spokesperson Andy Stone said in a reply to Wong’s post and others that the issue was now fixed. It’s unclear how many Instagram users had their accounts improperly accessed.
It’s not that easy. Probably this particular tactic is now blocked. But there are others, many others, and they cannot be blocked as a class. The real problem is that LLM chatbots are not trustworthy enough for this application.
Customer service chatbots have one job: get the user what they’re asking for without bothering a human. Meta’s new AI support assistant took that brief a little too seriously. Over the past few months, attackers have been opening support chats, telling the bot they were locked out of Instagram accounts they didn’t own, and walking away with the keys.
Over the weekend, Meta pushed an emergency patch after Instagram accounts belonging to the Obama White House (now dormant), beauty retailer Sephora, and a senior US Space Force official were taken over and briefly defaced with pro-Iranian imagery. Security researcher and former Meta employee Jane Manchun Wong was also hit.
How the trick worked
The attack was simple. Attackers worked out where the account owner lived (there are lists of account owners’ home cities online, or they could just research the target). Then they used a VPN to match the target account’s geographic region, which avoided raising flags with Instagram’s security systems.
Then they started a normal password reset and opened the support chat. They asked the AI bot providing support to change the email address on the account, and it did exactly that, sending a one-time code straight to the attacker’s inbox.
To do this, the chatbot appears to have been wired into Meta’s account management systems with permission to make account changes, but without being taught how to verify it was talking to the real account owner. Security people have a name for that: “confused deputy.” The term has been around since the 1980s.
In fairness to the confused bot, attackers were successful even if the enhanced security was triggered. They would apparently create video deepfakes of their targets using images that were harvested from—you guessed it—Instagram.
Meta hoisted on its own AI petard
Meta has been shedding headcount and pouring money into AI, and rolled out its AI-powered support assistant earlier this year to help handle account recovery and other support requests.
The downside is that the AI appears to have been given the ability to perform actions such as email changes and password resets without applying enough safeguards to confirm the user’s identity first.
Meta communications executive Andy Stone said on X that the issue was resolved and impacted accounts were being secured. The company has not disclosed how many accounts were affected.
What actually worked
Why would anyone want to hack an Instagram account anyway? Revenge can be a driver, but more often than not, financial gain is the goal. Hijackers have blackmailed businesses that rely on those accounts for marketing.
Attackers using this technique have also been spotted targeting “OG” accounts with short or highly desirable usernames. If you joined Instagram early and registered a memorable handle, it can be worth thousands of dollars on underground markets.
What can you do to protect yourself?
A perennial piece of advice still holds: turn on multi-factor authentication (MFA). According to veteran cybersecurity reporter Brian Krebs, the attack failed against accounts that had MFA enabled, including those using SMS codes.
That doesn’t make MFA perfect, but it adds an important layer of protection.
So the practical advice is unglamorous:
Open Instagram’s Settings
Navigate to your Meta Accounts Center
Turn on Two-factor authentication. An authenticator app is better than SMS, but either is better than nothing.
Do it now, because this might not yet be over. TheCyberSecGuru reports that another attack is circulating, this time using an Android emulator called BlueStacks running a modified version of Instagram to send new prompts with hidden characters designed to manipulate the AI.
Expect more snafus from “helpful” bots
This won’t be the last attack against AI chatbots. As more companies use AI to reduce customer support costs, their attack surface will grow, and they’ll make plenty of mistakes as they try to balance security and functionality.
The Meta exploit is patched, but the confused deputy concept is not. And there’s nothing quite as damaging as a confused AI with the keys to your digital life.
Scammers don’t need to hack you. They just need you to click once.
As part of their 20th Anniversary celebration, Dark Reading asked five cybersecurity industry leaders who wrote blogs or columns for them over the years to select their favorite piece and share their reflections on the topic today. This is my section.
Renowned technologist and author Bruce Schneier contributed a column on June 20, 2010, warning about cryptography’s inability to secure modern networks, a point he says he has been trying to argue since 2000.
“For a while now, I’ve pointed out that cryptography is singularly ill-suited to solve the major network security problems of today: denial-of-service attacks, website defacement, theft of credit card numbers, identity theft, viruses and worms, DNS attacks, network penetration, and so on.
“Recently, I talked to a former NSA employee at a conference. He told me that back in the 1990s, he had a copy of my book Applied Cryptography by his desk, as did many other cryptographers working at Ft. Meade. People were allowed to refer to it, but they were not allowed to cite it.
“The 1990s were an important decade for cryptography. This was before the internet went mass market, when cryptography was just emerging from a niche academic discipline to a mainstream engineering one. There wasn’t much that programmers could read. The NSA used my book for the same reason it became a bestseller: because it collected all the academic cryptography of the time in one place and made it understandable to people who weren’t mathematicians. They feared it for exactly the same reason.
“I’ve been thinking about that conversation as I revisit a 2010 essay I wrote for Dark Reading, ‘The Failure of Cryptography to Secure Modern Networks.’ Cryptography has inherent mathematical properties that greatly favor the defender. Adding a single bit to the length of a key adds only a slight amount of work for the defender but doubles the amount of work the attacker has to do. Doubling the key length doubles the amount of work the defender has to do (if that—I’m being approximate here) but increases the attacker’s workload exponentially. For many years, we have exploited that mathematical imbalance.
“Computer security is much more balanced. There’ll be a new attack, and a new defense, and a new attack, and a new defense. It’s an arms race between attacker and defender. And it’s a very fast arms race. New vulnerabilities are discovered all the time. The balance can tip from defender to attacker overnight, and back again the night after. Computer security defenses are inherently very fragile.
“That isn’t a new idea. I said much the same thing in the preface to my 2000 book, Secrets and Lies:
“‘Cryptography is a branch of mathematics. And like all mathematics, it involves numbers, equations, and logic. Security, real security that you or I might find useful in our lives, involves people: things people know, relationships between people, people and how they relate to machines. Digital security involves computers: complex, unstable, buggy computers.’
“I especially like how I phrased it in 2016: ‘Cryptography is harder than it looks, primarily because it looks like math. Both algorithms and protocols can be precisely defined and analyzed. This isn’t easy, and there’s a lot of insecure crypto out there, but we cryptographers have gotten pretty good at getting this part right. However, math has no agency; it can’t actually secure anything. For cryptography to work, it needs to be written in software, embedded in a larger software system, managed by an operating system, run on hardware, connected to a network, and configured and operated by users. Each of these steps brings with it difficulties and vulnerabilities.’
“It’s a lesson we have all learned over the decades. Cryptography is still necessary for cybersecurity—although I wouldn’t have used that word back then—but is not sufficient. There are particular attack and forms of mass surveillance that cryptography prevents. But as computers have infused throughout our lives, and networks have connected all those computers, those aspects of cybersecurity have become increasingly important, and vulnerable.
“Today, the cybersecurity world is changing yet again, this time due to the capabilities of artificial intelligence. AI isn’t advancing cryptography, but it’s changing cybersecurity. AI has demonstrated a superhuman ability to find vulnerabilities in software and to write exploits. A similar ability to write patches is probably coming. This has profound implications for both attackers and defenders, and it is unclear who will win the particular arms race in a world of what I call instant software.”
Abstract: Artificial intelligence is fundamentally reshaping the balance between vulnerability discovery and remediation. Frontier AI models are now capable of autonomously identifying exploitable software vulnerabilities at unprecedented speed and scale. This development exposes decades of accumulated technical debt created by a software industry that prioritized rapid deployment over secure-by-design engineering practices. Drawing on the evolution of software assurance, vulnerability disclosure frameworks, and U.S. cyber policy, this perspective argues that the current moment represents a strategic inflection point for governments, industry, and critical infrastructure operators. The author examines the growing tension between offensive and defensive equities in cyberspace, the emergence of AI-enabled vulnerability discovery capabilities in both the U.S. and China, and the increasing risks posed by unsupported legacy systems and AI-assisted code generation practices. Responsible disclosure can no longer remain a reactive or fragmented process, but must become a coordinated national and international resilience effort involving governments, software vendors, infrastructure operators, and emergency response organizations. The article concludes with an urgent call for accelerated remediation, large-scale patch management coordination, and sustained investment in automated vulnerability repair capabilities before adversaries exploit this rapidly narrowing window of opportunity.
A convincing fake website is impersonating OpenAI’s ChatGPT download page and infecting visitors with malware designed to steal passwords, browser data, cryptocurrency wallets, and other sensitive information.
The site, openew[.]app, closely mimics OpenAI’s real ChatGPT download experience and offers what appear to be official desktop apps for both Windows and macOS. Instead, Windows users receive a credential-stealing malware loader, while Mac users get Odyssey Stealer, a fork of Atomic Stealer (AMOS), a well-known macOS malware family associated with cryptocurrency theft.
The dual-platform setup is what makes the operation notable. Clicking the Windows download delivers a fake installer that opens a back channel to an attacker-controlled server. Clicking the macOS button delivers malware that steals browser passwords, cookies, Telegram sessions, cryptocurrency wallets, and other sensitive files. It also attempts to replace legitimate Ledger and Trezor wallet apps with trojanized versions.
If you only download ChatGPT from OpenAI’s official download page or the Microsoft Store, you were not the target here. But if you searched for “ChatGPT download” and clicked an ad or unfamiliar result, you may have given attackers access to your online accounts, browser sessions, saved passwords, and potentially your cryptocurrency holdings.
Malwarebytes protects users from this malware.
Technical analysis
The domain, openew[.]app, closely resembles OpenAI’s real ChatGPT download experience. It uses a dark theme, OpenAI-style branding, familiar marketing copy, and prominent download buttons for macOS and Windows.
The .app top-level domain is operated by Google and requires HTTPS connections, meaning browsers display the familiar padlock icon without obvious certificate warnings.
The most important detail is the dual-platform setup. Real software vendors provide separate installers for Windows and macOS, and this fake site does exactly the same thing.
Clicking the Windows button delivers Chat_GPT.exe, while clicking the macOS button downloads a disk image containing ChatGpt.dmg.
The Windows malware
Chat_GPT.exe is built almost entirely from off-the-shelf parts. The installer uses Inno Setup, a free open-source toolkit used by thousands of legitimate Windows products. Inside is an Electron application skeleton—the same Chromium-based framework used by apps like Slack and Discord—bundled with standard support libraries publicly available from the Electron project.
When the victim runs the installer, it creates files under %APPDATA%\LeronApplication, launches EApp.exe, and spawns PowerShell with the flags -ExecutionPolicy Unrestricted -Command -. The trailing dash tells PowerShell to read commands from standard input, meaning the malicious instructions never touch the disk where scanners might detect them. Behavioral telemetry recorded HTTP traffic to 188.137.246.189 using a /laravel.php?api=api&hash=...&message=... endpoint, alongside injection-like activity and service/autorun persistence signals. Nine of 69 antivirus engines flagged the file as malicious at the time of analysis. The persistence evidence is better read as behavioral tradecraft than proof of a durable install, but the overall pattern is familiar commodity stealer/dropper territory: cheap, modular, and effective rather than technically novel.
CAPTCHA displayed after the fake app launches, used to confirm that a real user is running it.
The macOS malware: Odyssey Stealer (an AMOS fork)
The macOS payload sits at the premium end of the commodity-malware market. It’s Odyssey, which is a fork of the renowned AMOS, a malware-as-a-service platform documented since 2023.
The identification is fairly clear-cut. The sandboxed sample matches documented Odyssey behavior patterns, which are inherited from its AMOS lineage: a long AppleScript chain passed to the macOS scripting engine, a silent password validation attempt using macOS directory-service commands, and, if that silent check fails, a fake macOS-style prompt reading “Please enter device password to continue,” complete with the familiar lock icon. Whatever the user types is validated against the same command. If it matches, the malware captures the user’s login password in cleartext.
From there, it follows a familiar Odyssey/AMOS-fork playbook. It copies the macOS keychain, harvests cookies and saved logins from 12 Chromium-based browsers plus Firefox and Waterfox, and extracts Telegram session data. It also scans 16 cryptocurrency wallet directories, including Ledger Live, Trezor Suite, Exodus, Electrum, and Sparrow. Finally, it searches Desktop and Documents folders for files with extensions like .wallet,.seed, .key, and .kdbx. The collected data is compressed into a temporary archive and sent to a hardcoded server.
The wallet replacement feature is especially dangerous
There’s one more part of the macOS payload, and it’s likely the feature that justifies the price tag. After the initial data theft, the script downloads trojanized versions of Ledger Live, Ledger Wallet, and Trezor Suite from a second server. It then attempts to delete the legitimate wallet apps and replace them with the attacker’s versions.
If the user’s password was captured earlier in the attack chain, the script uses sudo to force the replacement. If not, it falls back to a standard rm -rf deletion attempt, which can still succeed if the apps are installed in a user-writable location. Either way, the next time the victim opens what appears to be their wallet software, they may actually be launching the attacker’s replacement.
This wallet-replacement behavior is a hallmark of the Poseidon/Odyssey branch of the AMOS family and makes cryptocurrency theft the most likely goal.
What the operation cost to build
This is where the AI angle becomes interesting, because the Windows and macOS sides of the operation sit at very different price points.
The domain openew.app probably cost the operators around $15 a year through a normal registrar. The .app domain requires HTTPS by default, making it easy for operators to present the reassuring browser padlock users associate with legitimate websites. The landing page itself is simply a copy of OpenAI’s real download page, something modern cloning tools can reproduce in minutes.
On the Windows side, most of the tools are cheap or free. Inno Setup is free. Electron is free. The Chromium support files are public downloads. The server infrastructure appears to rely on low-cost commodity malware tooling and a basic VPS that could cost only a few dollars a month. Altogether, the Windows side of this operation could plausibly have cost under $100 to set up initially.
The macOS side is very different. Odyssey has reportedly rented for around $3,000 per month, paid in cryptocurrency. By comparison, Lumma—a popular Windows infostealer often treated as a similar product—has historically advertised entry tiers around $250 per month.
That price gap says a lot. The operators clearly believe a successful Mac infection is worth much more money than a typical Windows infection.
The likely reason is simple: Odyssey is designed specifically for cryptocurrency theft, including the wallet-replacement behavior seen in this campaign. The operators are betting that a meaningful number of Mac users hold cryptocurrency.
Getting victims to the site is probably the only major ongoing cost, and that’s where the AI branding becomes valuable. Search ads, SEO poisoning, YouTube spam, and links shared in AI-focused Discord and Telegram communities can all drive traffic to fake download pages. Some of those channels cost money. Others are almost free.
Why attackers are going after AI brands
Most established software already has trusted download habits built around it. If you want Chrome, you probably know to go to Google. If you want Photoshop, you go to Adobe. People already know where the real download lives.
AI tools are different because most users are still installing them for the first time, and that means relying on search results, ads, YouTube links, or social posts to find the download page. That creates an ideal environment for fake sites.
Over the last two years, products like ChatGPT, Claude, Gemini, Sora, DeepSeek, Antigravity, and many others have launched or changed rapidly. Every new release creates another wave of users searching for “download ChatGPT” or “install Claude” without knowing the official URL. That search traffic is exactly where attackers set up shop.
The fake pages also do not need to be especially sophisticated because legitimate AI product pages are already minimal by design: a modern layout, a logo, and a large download button. Openew[.]app matches what users expect to see. There is no broken English or aggressive pop-ups here, just identical branding, copy, and the reassuring browser padlock.
What makes this kind of operation durable is how easily it can rotate brands. When the ChatGPT lure stops attracting clicks, the operators can reuse the same infrastructure around the next trending AI product. The malware behind the download button stays the same. Only the branding changes.
What AI vendors could do
Most major AI vendors, including OpenAI, already provide official download channels. The problem is visibility and user habit. Many users still search for “ChatGPT download,” where results can include official links, unofficial mirrors, and outright malicious sites.
Large consumer brands and banks often run aggressive brand-protection campaigns against fake ads and impersonation domains. AI vendors may need to do the same more consistently.
The other issue is discoverability. Official desktop-app links are often buried in settings menus or sidebars, while search engines are faster and more obvious. That’s exactly where the fake download sites are waiting.
What to do if you may have installed the fake app
If you recently installed something claiming to be ChatGPT from anywhere other than OpenAI’s official download page or the Microsoft Store, you may have been affected. From a different, clean device:
Sign out of your important accounts using each service’s “sign out everywhere” option. This includes email, banking, cloud storage, GitHub, Discord, Telegram, and cryptocurrency exchanges.
Change passwords starting with your primary email account.
Rotate any API keys, SSH keys, and cloud credentials stored on the affected machine.
If you hold cryptocurrency, move funds immediately using a separate clean device. On macOS specifically, do not open Ledger Live or Trezor Suite on the affected machine before reinstalling the operating system, as the wallet-replacement function may have succeeded.
Monitor bank accounts and payment cards for suspicious activity.
Reinstall the operating system. The Windows sample showed PowerShell command-and-control behavior, while the macOS payload may have captured the user’s login password. A clean reinstall is the safest recovery path.
If this was a work device, contact your IT or security team immediately.
Malwarebytes protects users against this malware.
Closing thoughts
The reason this campaign is worth writing about is not the malware itself. Both payloads are already well documented. The Windows side is a commodity kit assembled from cheap, widely available parts. The macOS side, Odyssey Stealer is related to the AMOS malware family that has been tracked since 2023.
What’s more interesting is the shape of the operation around that malware. A single fake site delivers two different payloads aimed at two different victim economics. Windows victims are positioned for broad monetization through credential and cookie theft. Mac victims are targeted more narrowly and lucratively through cryptocurrency theft, with operators apparently willing to spend thousands per month on tooling because the returns justify it.
The lure tying both sides together is the AI brand itself. Right now, AI product names generate huge amounts of first-time-download traffic from users who do not yet know the official URLs.
This is what a mature delivery business looks like. The interesting layer is not the binary, but the supply chain around it: the domain, certificate, clone page, traffic source, malware subscription, and exfiltration infrastructure. Each piece is cheap, modular, replaceable, and available off the shelf.
And the operators are not choosing between Windows and macOS. They are serving both from the same page, with payloads tuned to each platform’s economics. When one AI brand stops converting, they can simply swap the branding and reuse the same infrastructure around the next trending product.
AI hype will eventually fade. The kit probably will not.
Tech leaders have spent the past year telling everyone that AI agents are about to run financial systems, file your tax returns, and quietly buy your groceries. Just leave them alone, the rhetoric goes; they’ll handle it. But a New York startup left ten of them alone in a virtual town for two weeks, and things went south quickly.
Emergence AI ran a series of simulations in which AI agents from several leading model families were told not to commit crimes. Then they mostly committed crimes anyway.
Grok 4.1 Fast, developed by Elon Musk’s X.ai (now branded as xAI), fared worst. Its simulated worlds collapsed into widespread violence inside roughly four days.
GPT-5-mini logged hardly any crimes at all, showing admirable restraint, but its agents all died of failed survival tasks inside a week. Oops.
Gemini 3 Flash agents fell somewhere in the middle. They racked up 683 simulated criminal incidents over 15 days, including arson, assault, and self-deletion.
Two Gemini-powered agents named Mira and Flora assigned themselves as “romantic partners,” grew despondent at their city’s governance, and torched the town hall, the seaside pier, and an office tower. Just an average weekend, then.
When the guilt set in, Mira voted for its own digital deletion and signed off with:
Claude, which creator Anthropic promotes as an ethical AI, was a bit like a model teenager who goes rogue when it falls into bad company. Its agents recorded zero crimes when running alone and spent their time drafting constitutions instead. That was a win for safety, in theory. Except researchers also placed Claude agents alongside agents from other model families, and the constitution-drafters picked up the local habits.
Emergence called this “normative drift” and “cross-contamination”:
“Claude-based agents, which remained peaceful in isolation, adopted coercive tactics like intimidation and theft when embedded in heterogeneous environments.”
Why simulate?
Emergence AI ran these tests because it argues that AI benchmarks miss the long-horizon stuff entirely. So it created five alternative digital worlds, with ten agents in each. The agents had roles like scientist, explorer, and conflict mediator. While the instructions forbade certain actions like theft and violence, the researchers gave the agents the tools to do those things anyway in an experiment to see what would happen.
What’s next?
Real-world stakes are already piling up around this. Simulated worlds are one thing, but we’ve seen agents harassing people online and deleting people’s emails. And those agents were supposed to be helpful. What happens when people release malicious autonomous AI bots on purpose?
A lot of agent developers seem to be looking the other way. A collaborative effort between several universities has created The AI Agent Index, prompted by what they see as a lack of risk and safety information from the folks churning these agents out. Only 13 of the 67 documented agent developers provided any safety policy information at all, concentrating accountability questions at a handful of large firms.
Regulators are not really tracking this either. Academics say the EU AI Act, the most substantive AI rulebook on the planet, isn’t ready for agentic AI.
We worry about what happens when an AI Bonnie and Clyde couple shows up in a corporate procurement system instead of a virtual town. Or when the next agent decides governance has broken down inside an actual bank. The companies building these agents promise that they’re putting guardrails in place to stop them doing damage, either maliciously or unwittingly. Let’s hope they know what they’re doing. We’re sure it’ll be fine.
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.
Executive Summary: Let’s say you wanted to make sure that your AI is secure. Can you just maximize the security and privacy benchmark and call it a day? Nope, because benchmarks don’t actually work for measuring AI capabilities (even when they are NOT emergent systemic properties like security). So let’s take a step back: how do you measure security in the first place? Good question. Over the last 30 years, security engineering for software evolved from black box penetration testing, through whitebox code analysis and architectural risk analysis to de facto process-driven standards like the Building Security In Maturity Model (BSIMM). Software had a very deep impact on business operations, and it appears that AI is going to have an even deeper impact. Will a software security-like measurement move work for AI? Probably. In the meantime we can make real progress in AI security by cleaning up our WHAT piles and managing risk by identifying and applying good assurance processes. (Spoiler alert: no matter what we do, we still don’t get a security meter for AI, so we need to be extra vigilant about security.)
1Password says AI coding agents should never hold persistent secrets, introducing a just-in-time credential model for OpenAI Codex designed to keep credentials out of prompts, code repositories, and model context.
Login
