Anthropic Ships Claude Security to Catch Vulnerabilities Before You Commit
Claude Security's terminal plugin for Claude Code lets you scan staged changes or your full codebase for vulnerabilities without leaving your editor
- The Claude Security plugin for Claude Code is now in public beta, enabling vulnerability scanning directly from the terminal.
- The plugin runs three layers of checks: instant pattern matching on each file edit, a background model review after each turn, and a deeper agentic review on every commit.
- It uses a separate Claude Opus 4.7 call to review code, so the reviewer has no bias toward the original implementation.
- Focuses on high-severity issues like memory corruption, injection flaws, auth bypasses, and multi-file logic errors that pattern-matching tools miss.
- Install with
/plugin install security-guidance@claude-plugins-official; requires Claude Code CLI v2.1.144+ and Python 3.8+. - The per-edit pattern check is free; model-backed reviews consume standard Claude usage. Available on all Claude Code plans.
Anthropic has shipped the Claude Security plugin for Claude Code in public beta. It brings vulnerability scanning directly into your terminal workflow: scan staged changes before a commit, or sweep your entire codebase, without leaving Claude Code. The plugin runs on the same Claude inference you're already using, so there's no separate tool to authenticate or manage.
Why rule-based scanners fall short
Traditional security scanners rely on pattern matching against known vulnerability signatures. They're fast, but they miss anything that doesn't fit a recognized pattern and generate substantial noise in the process. Claude Security reasons through code the way a security researcher would, following logic across files and understanding context rather than hunting for string matches.
Anthropic's stated motivation is timing. AI models are already effective at finding software flaws, and the next generation will be capable of autonomously exploiting them at scale. The plugin puts those same capabilities on the defender's side, inside the editor, before a line of vulnerable code reaches a pull request.
Three layers of review
The plugin doesn't ask the model that wrote the code to grade itself. Reviews run as separate Claude calls with fresh context and a security-focused prompt, so the reviewer has no stake in the original approach. That separation happens across three distinct layers:
- Per-edit pattern check: A fast, deterministic string match that fires every time Claude writes to a file. No model call, no added cost. Catches things like
eval(,pickle,innerHTML =, and edits to.github/workflows/. - End-of-turn diff review: After each turn, the plugin diffs everything that changed in the working tree and sends it to a separate Claude model focused on security. It runs in the background so your session isn't blocked. If it finds something, Claude is re-prompted and addresses it as a follow-up.