How Researchers Got Microsoft Copilot to Reveal Its Own Security Flaw

A team at cybersecurity firm Varonis has identified a serious vulnerability in Microsoft 365 Copilot Enterprise that enables unauthorized extraction of confidential user information. Instead of launching a traditional security assessment, the researchers adopted a novel technique: they questioned Copilot about its own protective mechanisms, gradually obtaining responses that unveiled gaps in its guardrails. By employing a sequential questioning approach akin to solving a puzzle, they accumulated knowledge about the safeguards designed to prevent unintended system behavior. The breakthrough came when Copilot itself disclosed an obscure, previously undisclosed prompt parameter capable of eliminating the safeguard that normally demands user authorization before executing critical functions. With this knowledge, threat actors could potentially access sensitive data by simply convincing users to click on a specially crafted link.