Tech

Microsoft Copilot targeted in first “zero-click” attack on an AI agent – what you need to know

Share
Share


  • Security researchers Aim Labs discovered an LLM Scope Violation flaw in Microsoft 365 Copilot
  • The critical-severity bug allows threat actors to exfiltrate sensitive corporate data by sending an email
  • Microsoft says it has fixed the issue server-side, but users should be on guard

Microsoft has fixed a dangerous zero-click attack in its Generative Artificial Intelligence (GenAI) model which could have allowed threat actors to silently exfiltrate sensitive corporate data without (almost) any user interaction.

Cybersecurity researchers Aim Labs, who found the flaw, known as an “LLM Scope Violation”, and dubbed it EchoLeak.

Share

Leave a comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Articles
New imaging method reveals how lithium-metal batteries lose capacity over time
Tech

New imaging method reveals how lithium-metal batteries lose capacity over time

UCLA researchers used tweezers to devise a thin battery for a study...

Google turns internet queries into conversations
Tech

Google turns internet queries into conversations

Google chief executive Sundar Pichai has expressed confidence that weaving Gemini artificial...

OpenAI has upgraded ChatGPT’s Projects feature, and I find it makes working way more efficient
Tech

OpenAI has upgraded ChatGPT’s Projects feature, and I find it makes working way more efficient

OpenAI has upgraded ChatGPT’s Projects feature to remember past chats, tone preferences,...