A poisoned npm package infected 140+ projects with a hidden payload. This report highlights how to detect, hunt, and defend ...

SearchLeak and a three-CVE LiteLLM chain broke the same AI trust boundary in two weeks. A 5-check audit maps each gap to a ...

Azure Functions shipped a serverless agents runtime in public preview at Build 2026. Agents are defined in .agent.md markdown ...

Microsoft’s AutoJack research shows how a malicious webpage rendered by an AI browsing agent can reach local MCP services and ...

One previously unreported SpaceX investor has ties to Chinese military contractors. The information was revealed only after ProPublica went to court to obtain it. The United States is requiring access ...

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 ...

Apple’s AI plans show promise, but proof of success still to come — analysts Apple is promising AI today, not tomorrow — so how is the tech industry reacting to Monday’s keynote announcements? With a ...

A long-running phishing operation has turned GitHub Pages into a low-cost staging ground for fake banking portals aimed at customers of financial institutions operating in Mexico, harvesting logins, ...

Microsoft has disclosed details of a Windows-based cryptocurrency clipper campaign codenamed CryptoBandits that has targeted users since February 2026 with clipboard-intercepting malware with ...