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
npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a claude-codeWhat 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
maintofeature-branchand 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-code2Manually: put the files in place
~/.claude/skills/commit-security-scan/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/commit-security-scan/
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a codex2Manually: put the files in place
.agents/skills/commit-security-scan/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a cursor2Manually: put the files in place
.cursor/skills/commit-security-scan/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Factory-AI/factory-plugins plugins/security-engineer/skills/commit-security-scan2Manually: put the files in place
.github/skills/commit-security-scan/SKILL.md1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a gemini-cli2Platform CLI
gemini skills install https://github.com/Factory-AI/factory-plugins --path plugins/security-engineer/skills/commit-security-scanManually: put the files in place
.devin/skills/commit-security-scan/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill commit-security-scan -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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.