Anthropic ships a beta security plugin for Claude Code with multi-agent scans
thione · x · 2026-07-27
Anthropic released a Claude Security plugin beta for Claude Code.
The plugin uses multi-agent scans to find vulnerabilities and propose patches, turning Claude Code into a more security-aware coding workflow rather than just a generic code assistant.
This is both a product update and a sign that Anthropic is pushing Claude Code toward deeper software-security use cases.
More from coding & agent
- AI One-Shots 25k Lines of Code to Simulate Black Hole Electrodynamics in 5 Minutes — kylekabasares · 2026-07-27
- ComfyUI adds Comfy MCP so agents can build workflows from prompts — PurzBeats · 2026-07-27
- Wiz says Atlas tops CyberGym with 90.9% and found 200+ new bugs — vijaybolina · 2026-07-27
- AI agent finds a longstanding Bun Node-compat bug in `child_process.spawn` — steipete · 2026-07-27
- How to connect Higgsfield to Claude and generate videos from chat — mhdfaran · 2026-07-27
- Claude plus Higgsfield MCP powers a one-chat workflow for faceless YouTube Shorts — mhdfaran · 2026-07-27