JFrog says six malicious npm packages used hidden install-time execution, JSONKeeper fetches, and sandbox checks to enable remote access.

Claude Code dynamic workflows are now generally available on all paid plans, including Pro for the first time. The feature writes its own orchestration scripts and coordinates up to 1,000 parallel ...

VS Code 1.127 enhances agent session management, introduces per-site browser permissions, and makes browser tools for agents ...

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

Both tools have a point, just different ones ...

Chainguard is expanding Repository with new policy controls, malware and greyware scanning, and support for Java, Python, and container artifacts-helping organizations govern software consumption ...

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 ...

Island found dormant JavaScript injection paths in Adblock for YouTube, a Chrome extension with 10M+ installs, raising ...

On March 17, 2026, MyCard, Inc. (d/b/a Knot) filed a bombshell complaint in the District of Delaware, alleging that it had caught Atomic FI, ...

The new “agentjacking” attack takes almost no real hacking ability to pull off. It's predicated on pulling a public ...

By turning the terminal into a live, collaborative canvas, Anthropic is proving that the most valuable output of an AI coding ...