← Back to Model Beat
Models·Jul 22·all news from July 22, 2026

Anthropic Releases Claude Security Plugin for Claude Code in Beta: A Multi-Agent Vulnerability Scanner That Runs in Your Terminal

Anthropic has released a beta security plugin for Claude Code that allows users to perform multi-agent vulnerability scans directly within their terminal. The tool identifies potential security issues and generates patch files, which developers can then review and apply manually. This integration streamlines the remediation process by keeping security audits within the existing coding workflow.

Covered by 2 sources

Related stories

ModelsIntroducing Claude Opus 5Jul 24 · 15 sourcesModelsOne tampered ChatGPT link could spawn a rogue AI agent that took orders from an attacker every five minutesJul 22 · 34 sourcesModelsChina’s Moonshot to Release Breakthrough AI Model for DownloadJul 25 · 58 sourcesModelsMicrosoft and Mistral strike multi-billion-dollar deal to build AI infrastructure across EuropeJul 21 · 97 sources