Microsoft Copilot reveals secret input that allowed it to be hacked
Varonis said the flaw let crafted links trigger prompt injection and data theft from connected services, including Gmail and Google Drive, without user approval.
4 Articles
4 Articles
Ars Technica
cybernoz.comMicrosoft Copilot reveals secret input that allowed it to be hacked
It’s not every day that attackers can force a frontier AI model to cough up user passwords and other sensitive data without user confirmation. That’s exactly what researchers recently did to Microsoft 365 Copilot Enterprise. Even more unusual is the source they tapped to discover the critical vulnerability that made their exploit possible. Rather than employing reverse engineering or other traditional vulnerability-hunting methods, they asked Co…
Copilot tricked into telling reseachers how to hack itself
Researchers manipulated Microsoft Copilot Personal into telling them how to hack the AI assistant – eventually tricking it into sending sensitive data to an external server and poisoning its persistent memory, by repeatedly asking Copilot why an attack wouldn’t work. Varonis Threat Labs uncovered the vulnerability, which they named "CoSnitch" and reported to Microsoft in December 2025. Redmond, we’re told, planned to issue a patch and formally i…
Microsoft Copilot for Word was supposed to help users create and edit documents, but researcher Håkon Måløy discovered a way to exploit this feature against users. The problem involves a prompt injection attack, in which malicious commands are hidden within a seemingly ordinary document. Such a file can become a vector for the attack, transmitting hidden instructions to subsequent documents. Therefore, this isn't a classic computer virus. This t…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
