Anthropic's Security Guidance Plugin Shields Claude Code Projects from Vulnerabilities Before Commit

Anthropic has released a free Security Guidance plugin for Claude Code that automatically identifies and helps remediate over 25 vulnerable code patterns before developers push changes, addressing a critical shift-left security need in AI-assisted development. The plugin, which became available through Anthropic's official marketplace in May 2026, conducts security checks at three distinct phases: as developers edit files, at the end of each interaction turn, and when code is committed or pushed to version control.