This Microsoft Copilot vulnerability only requires a single click, and your personal data could be stolen
The Reprompt attack can bypass security controls without detection
Here at Tom’s Guide our expert editors are committed to bringing you the best news, reviews and guides to help you stay informed and ahead of the curve!
You are now subscribed
Your newsletter sign-up was successful
Want to add more newsletters?
Daily (Mon-Sun)
Tom's Guide Daily
Sign up to get the latest updates on all of your favorite content! From cutting-edge tech news and the hottest streaming buzz to unbeatable deals on the best products and in-depth reviews, we’ve got you covered.
Weekly on Thursday
Tom's AI Guide
Be AI savvy with your weekly newsletter summing up all the biggest AI news you need to know. Plus, analysis from our AI editor and tips on how to use the latest AI tools!
Weekly on Friday
Tom's iGuide
Unlock the vast world of Apple news straight to your inbox. With coverage on everything from exciting product launches to essential software updates, this is your go-to source for the latest updates on all the best Apple content.
Weekly on Monday
Tom's Streaming Guide
Our weekly newsletter is expertly crafted to immerse you in the world of streaming. Stay updated on the latest releases and our top recommendations across your favorite streaming platforms.
Join the club
Get full access to premium articles, exclusive features and a growing list of member rewards.
A flaw within Microsoft’s Copilot has been allowing attackers to steal the personal information of users with a single click. Called the ‘Reprompt’ exploit by the researchers at the Varonis Threat Labs, a new report from the data security research firm details the way that the vulnerability permits attackers to gain an entry point to perform a data-exfiltration chain that bypasses security controls to access data without detection.
According to the researchers, an attacker using the Reprompt exploit would send a user a phishing link. Once the link was opened, it would begin a multi-stage prompt injection process that uses a ‘q parameter.’ This would enable the attacker to request information about the victim from Copilot, such as the victim's address or the files they recently viewed. They could access this data even if Copilot was closed.
The researchers had found that "By including a specific question or instruction in the Q parameter, developers and users can automatically populate the input field when the page loads causing the AI system to execute the prompt immediately."
This means that an attacker could issue a Q parameter that asks Copilot to send data back to the attacker's server, even though Copilot is designed to specifically refuse to fetch URLs like this. Varonis researchers were able to engineer prompts to Copilot in ways that bypassed safeguards and asked the AI to fetch the URL in a way that the AI wasn't designed to.
How to stay safe from Reprompt
The good news is that the exploit has already been reported to Microsoft way back in August of 2025, and has been patched this week, so it has been fixed. That means there is currently no risk of it impacting users, particularly if you regularly update your operating system with available patches and updates.
However, it’s still recommended that users be extremely careful about what kind of information they share with their AI assistants and be on the lookout for phishing attempts. That means don't click on links that get sent to you from unexpected sources, especially ones that link to your AI assistant of choice.
Because Reprompt initiates from a phishing link, it is particularly important to follow the guidelines to protect yourself against phishing attempts. Don't open or click anything you're not expecting, especially if it uses urgency or threatening language. Hover over links to see where they redirect to. Use one of the best antivirus programs, and make sure you've enabled all the features it offers to help keep you safe online, such as browser warnings, a VPN and anti-phishing measures.
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.
Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds.
More from Tom's Guide
- Fake Grok app built using generative AI discovered spreading malware on macOS devices
- Microsoft's first Patch Tuesday of 2026 fixes over 100 bugs and one active zero-day flaw — don't wait to update your PC
- Instagram denies data breach of 17 million users after password reset email wave — here's what to do next

Amber Bouman is the senior security editor at Tom's Guide where she writes about antivirus software, home security, identity theft and more. She has long had an interest in personal security, both online and off, and also has an appreciation for martial arts and edged weapons. With over two decades of experience working in tech journalism, Amber has written for a number of publications including PC World, Maximum PC, Tech Hive, and Engadget covering everything from smartphones to smart breast pumps.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.
