Skip to main content
skill CX Codex

commit-security-scan — Claude Code skill: install

The commit-security-scan skill reviews Git changes for security flaws using threat-model context. Use it for pull requests, staged files, or branch diffs.

no license 126 installs ★ 129 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a claude-code
Open on GitHub

What commit-security-scan does

commit-security-scan reviews commits, pull requests, commit ranges, staged work, uncommitted files, and branch comparisons. It reads the changed files and traces data through code to look for weak authentication or authorization, injection risks, exposed secrets, insecure object access, and denial-of-service patterns. The checks follow STRIDE categories and the repository’s threat model.

The scan relies on .factory/threat-model.md and .factory/security-config.json. Without both files, scanning cannot proceed; the skill first invokes threat-model-generation to create them. It then gathers changes with Git or gh pr diff, checks possible findings against existing safeguards and severity thresholds, and writes security-findings.json with the affected code, risk level, reasoning, and suggested fix.

What it helps with

  • scan a pull request for vulnerabilities
  • check staged changes before a commit
  • compare two branches for security issues
  • review a commit range against the threat model
  • trace user input to a risky code sink

Example prompts for the agent

  • Scan PR #456 for security vulnerabilities.
  • Check my staged changes for security issues before I commit.
  • Scan changes from main to feature-branch and write the findings report.

How to install commit-security-scan

1Skills CLI (Vercel)

npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a claude-code

2Manually: put the files in place

~/.claude/skills/commit-security-scan/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/commit-security-scan/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about commit-security-scan

How do I install commit-security-scan in Claude Code?

Run npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a claude-code, then use ~/.claude/skills/commit-security-scan/SKILL.md.

What does commit-security-scan do?

It examines Git changes for security weaknesses across STRIDE categories, including injection, authorization failures, secret exposure, and resource exhaustion. The result is written to security-findings.json.

What must exist before a scan starts?

The repository needs .factory/threat-model.md and .factory/security-config.json. If either file cannot be read, the skill invokes threat-model-generation first.

Similar skills

All skills for Security →

From the same set17

The whole set →
fix-knip-unused-exports fix-knip-unused-exports resolves knip “Unused exports” violations by removing or relocating exports that have no production consumers. Use when npm run knip reports unused code. CX Codex +1 147installs skill-creation skill-creation converts past session breakthroughs into reusable agent skills inside SKILL.md files. Helps extract repeatable patterns and refine existing instructions. CX Codex +1 142installs autoresearch The autoresearch skill runs repeated code experiments against a measurable target. Use it for tuning tests, builds, bundle size, or ML training results. CX Codex +1 137installs vulnerability-validation vulnerability-validation is a Claude Code skill that tests whether security scan findings can be exploited and filters false alarms. It runs after commit-security-scan, before findings become issues or block a PR. CX Codex +1 135installs http-toolkit-intercept http-toolkit-intercept captures HTTP requests and responses from any script or service — including LLM API calls, backend requests, and auth flows. Use it when you need to see what's actually sent over the wire and what comes back. CX Codex +1 124installs browser-navigation browser-navigation automates browser tasks: page navigation, form filling, screenshots, data extraction, and session recording. CX Codex +1 120installs droid-control droid-control is a skill for automating terminal TUIs, browsers, and desktop apps. Record demos, run tests in real environments, and capture QA proof. CX Codex +1 118installs follow-up-on-pr follow-up-on-pr takes an open pull request, rebases on the target branch, resolves reviewer comments, runs local verification, and pushes updates. CX Codex +1 117installs

Project sponsors

Companies that keep this analytics open