# anthropics/claude-code-security-review

An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.

Repository: https://github.com/anthropics/claude-code-security-review
Canonical: https://ross.abutalabs.com/products/claude-code-security-review
Language: Python
License: MIT
License Family: permissive
Last push: 2026-02-11T18:01:23+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 35, longevity 28
- inputs: {"age_days": 394, "days_push": 203, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6093, forks 660 (observed 2026-08-28T04:09:34.955905+00:00)

## What it is
A GitHub Action that uses Anthropic's Claude to perform AI-powered security reviews of pull requests, analyzing code diffs for vulnerabilities with semantic understanding. It automatically comments findings on PRs and filters false positives.

## Use cases
- automate security review of pull requests
- detect vulnerabilities in code changes with AI
- add AI code review to GitHub Actions CI
- reduce false positives in security scanning
- review PR diffs for security issues before merge

## When to choose
- you want automated, context-aware security analysis on every PR
- your team uses GitHub and wants findings as PR comments
- you need language-agnostic vulnerability detection beyond pattern matching

## When to avoid
- PRs come from untrusted contributors, since the action is not hardened against prompt injection
- you need guaranteed deterministic or compliance-certified scanning
- you cannot share code with the Claude API due to privacy constraints

## Facets
- artifact type: plugin
- maturity: active
- function: security, vulnerability-scanning, code-review, ci-cd, llm-inference
- domain: security, developer-tools, version-control, large-language-models
- platform: cloud, python
- tags: github-action, ai-security-review, pull-request, claude, static-analysis, devsecops, docker

## Member repositories
- anthropics/claude-code-security-review (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.955905+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:48:17.313474+00:00, confidence not recorded.
  - readme: https://github.com/anthropics/claude-code-security-review (fetched 2026-08-28T04:09:34.955905+00:00, sha a5897df98e38)
- Data as of 2026-08-30T08:39:29.467469+00:00.