Skip to content
  1. Home
  2. AI tools
  3. Claude Code Security Reviewer

Claude Code Security Reviewer

GitHub Action that reviews pull-request diffs for vulnerabilities

What it is

A GitHub Action from Anthropic that uses Claude Code to analyse the changed files in a pull request for security issues and posts findings as PR comments. It works on any language, reasons about code semantics instead of matching patterns, and filters likely false positives.

Good for

  • Add a security pass to every pull request
  • Catch injection or auth bugs in a diff
  • Comment findings directly on the PR

What you need

Anthropic API key enabled for the Claude API and Claude Code; GitHub Actions

Worth knowingThe README warns it is not hardened against prompt injection: use it on trusted PRs only.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for security & quality

See the topic →
  • Security Guidance plugin

    NousResearch/hermes-agent

    Warns when written code contains known-dangerous patterns

    ToolGitHub stars: 263k
  • security-guidance

    anthropics/claude-plugins-official

    Security warnings on edits plus LLM diff review

    ToolGitHub stars: 47k
  • Langfuse

    langfuse/langfuse

    Open-source tracing, evals and cost tracking for LLM applications

    ToolGitHub stars: 37k
  • Promptfoo

    promptfoo/promptfoo

    CLI for evaluating and red-teaming prompts, agents and RAG apps

    ToolGitHub stars: 27k