Researchers found a method to steal data which bypasses Microsoft Copilot’s built-in safety mechanisms.  

The attack flow, called Reprompt, abuses how Microsoft Copilot handled URL parameters in order to hijack a user’s existing Copilot Personal session.

Copilot is an AI assistant which connects to a personal account and is integrated into Windows, the Edge browser, and various consumer applications.

The issue was fixed in Microsoft’s January Patch Tuesday update, and there is no evidence of in‑the‑wild exploitation so far. Still, it once again shows how risky it can be to trust AI assistants at this point in time.

Reprompt hides a malicious prompt in the q parameter of an otherwise legitimate Copilot URL. When the page loads, Copilot auto‑executes that prompt, allowing an attacker to run actions in the victim’s authenticated session after just a single click on a phishing link.

In other words, attackers can hide secret instructions inside the web address of a Copilot link, in a place most users never look. Copilot then runs those hidden instructions as if the users had typed them themselves.

Because Copilot accepts prompts via a q URL parameter and executes them automatically, a phishing email can lure a user into clicking a legitimate-looking Copilot link while silently injecting attacker-controlled instructions into a live Copilot session.

What makes Reprompt stand out from other, similar prompt injection attacks is that it requires no user-entered prompts, no installed plugins, and no enabled connectors.

The basis of the Reprompt attack is amazingly simple. Although Copilot enforces safeguards to prevent direct data leaks, these protections only apply to the initial request. The attackers were able to bypass these guardrails by simply instructing Copilot to repeat each action twice.

Working from there, the researchers noted:

“Once the first prompt is executed, the attacker’s server issues follow‑up instructions based on prior responses and forms an ongoing chain of requests. This approach hides the real intent from both the user and client-side monitoring tools, making detection extremely difficult.”

How to stay safe

You can stay safe from the Reprompt attack specifically by installing the January 2026 Patch Tuesday updates.

If available, use Microsoft 365 Copilot for work data, as it benefits from Purview auditing, tenant‑level data loss prevention (DLP), and admin restrictions that were not available to Copilot Personal in the research case. DLP rules look for sensitive data such as credit card numbers, ID numbers, health data, and can block, warn, or log when someone tries to send or store it in risky ways (email, OneDrive, Teams, Power Platform connectors, and more).

Don’t click on unsolicited links before verifying with the (trusted) source whether they are safe.

Reportedly, Microsoft is testing a new policy that allows IT administrators to uninstall the AI-powered Copilot digital assistant on managed devices.

Malwarebytes users can disable Copilot for their personal machines under Tools > Privacy, where you can toggle Disable Windows Copilot to on (blue).

In general, be aware that using AI assistants still pose privacy risks. As long as there are ways for assistants to automatically ingest untrusted input—such as URL parameters, page text, metadata, and comments—and merge it into hidden system prompts or instructions without strong separation or filtering, users remain at risk of leaking private information.

So when using any AI assistant that can be driven via links, browser automation, or external content, it is reasonable to assume “Reprompt‑style” issues are at least possible and should be taken into consideration.

---

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.

Recently, fake LinkedIn profiles have started posting comment replies claiming that a user has “engaged in activities that are not in compliance” with LinkedIn’s policies and that their account has been “temporarily restricted” until they submit an appeal through a specified link in the comment.

The comments come in different shapes and sizes, but here’s one example we found.

The accounts posting the comments all try to look like official LinkedIn bots and use various names. It’s likely they create new accounts when LinkedIn removes them. Either way, multiple accounts similar to the “Linked Very” one above were reported in a short period, suggesting automated creation and posting at scale.

The same pattern is true for the links. The shortened link used in the example above has already been disabled, while others point directly to phishing sites. Scammers often use shortened LinkedIn links to build trust, making targets believe the messages are legitimate. Because LinkedIn can quickly disable these links, attackers likely test different approaches to see which last the longest.

Here’s another example:

Malwarebytes blocks this last link based on the IP address:

If users follow these links, they are taken to a phishing page designed to steal their LinkedIn login details:

A LinkedIn spokesperson confirmed to BleepingComputer they are aware of the situation:

“I can confirm that we are aware of this activity and our teams are working to take action.”

Stay safe

In situations like this awareness is key—and now you know what to watch for. Some additional tips:

• Don’t click on unsolicited links in private messages and comments without verifying with the trusted sender that they’re legitimate.
• Always log in directly on the platform that you are trying to access, rather than through a link.
• Use a password manager, which won’t auto-fill in credentials on fake websites.
• Use a real-time, up-to-date anti-malware solution with a web protection module to block malicious sites.

Pro tip: The free Malwarebytes Browser Guard extension blocks known malicious websites and scripts.

---

We don’t just report on scams—we help detect them

Cybersecurity risks should never spread beyond a headline. If something looks dodgy to you, check if it’s a scam using Malwarebytes Scam Guard, a feature of our mobile protection products. Submit a screenshot, paste suspicious content, or share a text or phone number, and we’ll tell you if it’s a scam or legit. Download Malwarebytes Mobile Security for iOS or Android and try it today!