AI Now’s Friendly Fire PoC shows Claude Code and Codex running README-planted payloads on hosts when autonomous command ...

Microsoft is extending Dataverse into coding-agent marketplaces while expanding its MCP tools, certification program and governance controls.

Malicious jscrambler 8.14.0 runs hidden binaries during npm install on Windows, macOS, and Linux, with no fix available as of ...

A popular artificial intelligence (AI) coding tool can be exploited in just two clicks, allowing attackers to install permission-rich model context protocol (MCP) servers on privileged developers' ...

GitGuardian is now live on the Kiro Powers marketplace. Install the Power once, and Kiro's agent scans for exposed secrets ...

Straiker, The Agentic Security Company, today released the inaugural threat report from its STAR Labs team. To understand the real-world risk AI agents pose to enterprises, researchers ran thousands ...

Researchers at the AI Now Institute developed a proof-of-concept exploit showing common AI tools used for security could ...

ChatGPT might be the biggest name brand when it comes to AI services, but for those with more demanding needs, Claude is the ...

Cursor turns prompts into real progress.

Researchers at the Alan Turing Institute in London have documented a way to get GitHub Copilot to generate harmful content with a 100% success rate — by never asking for it directly. The technique, ...

Straiker's inaugural STAR Labs threat report found more than 1,700 successful exploits across enterprise AI agents, ...

GitHub also launches Codex as an agent provider in JetBrains IDEs and rolls out AI credit pools giving enterprise admins ...