News

Microsoft Copilot targeted in first “zero-click” attack on an AI agent - what you need to know
Security researchers Aim Labs discovered an LLM Scope Violation flaw in Microsoft 365 Copilot The critical-severity bug ...
Microsoft is prepping an AI Copilot for the Pentagon
Microsoft is preparing a version of its Copilot AI tool for the Pentagon as it nears a deal to add 1 million new users from a ...
Researchers Just Found a Big Security Flaw in Microsoft’s AI. Here’s Why Businesses Should Worry
Microsoft’s been inserting AI everywhere it can, including into some of the world’s most popular business productivity apps.
CSO Online9h
First-ever zero-click attack targets Microsoft 365 Copilot
A single email can silently trigger Copilot to exfiltrate sensitive corporate data — no clicks, no warnings, no user action.
Microsoft is working on a deal to add 1 million Copilot users from a single customer, exec says in internal meeting
Chief Commercial Officer Judson Althoff told employees in a recent meeting that the software giant is working on this big ...
How To Conduct Red Teaming Of AI Copilots
Here, I'll outline how CISOs can assign red teams to hunt for such files, some examples of real-world findings and suggested ...
Microsoft fixes first known zero-click attack on an AI agent
EchoLeak affected Microsoft 365 Copilot, the AI assistant integrated across several Office applications, including Word, ...
Exclusive: New Microsoft Copilot flaw signals broader risk of AI agents being hacked—‘I would be terrified’
Microsoft 365 Copilot, the AI tool built into Microsoft Office workplace applications including Word, Excel, Outlook, ...