Microsoft Copilot was focused in the first “zero -click” -attack on an AI agent -what you need to know

• Security researchers AIM Labs discovered an LLM -Scope -violation error in Microsoft 365 Copilot
• With the bug of criticism of seriousness, threat actors can exfiled sensitive company data by sending an e-mail
• Microsoft says it has solved the server’s problem, but users must be on the guard

Microsoft Has solved a dangerous zero click attack in its generative artificial intelligence (Genai) model with which threat actors in silence sensitive company data can quietly exfiltrate without (almost) any user interaction.

CyberSecurity -Researchers Aim LabsWho found the mistake, known as an “LLM -Scope -violation”, and called the Echoleak.