Zero-Click Flaw in Microsoft Copilot Illustrates AI Agent, RAG Risks

agentic ai, security, Qevlar, funding,

Aim Security researchers found a zero-click vulnerability in Microsoft 365 Copilot that could have been exploited to have AI tools like RAG and AI agents hand over sensitive corporate data to attackers simply by issuing a request for the information in a specially worded email. Microsoft fixed the security flaw.

The post Zero-Click Flaw in Microsoft Copilot Illustrates AI Agent, RAG Risks appeared first on Security Boulevard.

This article has been indexed from Security Boulevard

Read the original article: