A vulnerability chain dubbed AutoJack in Microsoft’s AutoGen Studio interface for prototyping AI agents could let attackers manipulate an agent into executing arbitrary commands on its host system ...
ThreatsDay Bulletin covers AI abuse, poisoned packages, phishing, macOS attacks, SD-WAN flaws, scams, and supply-chain ...
Last Tuesday, Microsoft patched a vulnerability it rated as max critical in its M365 Copilot AI platform. On Monday, the ...
Microsoft details AutoJack exploit chain targeting AutoGen Studio MCP WebSocket in pre-release builds, enabling ...
A poisoned npm package infected 140+ projects with a hidden payload. This report highlights how to detect, hunt, and defend ...
Cloud storage providers love talking about security, but the jargon and technical language can leave users guessing. Here's a ...
Ongoing research into AI agent framework security identified an exploit chain in AutoGen Studio (AutoGen’s open-source prototyping user interface) that allows untrusted web content rendered by a ...