security-review · factory-ai — Claude Code skill: scan code for vulnerabilities
security-review scans code changes for security flaws using STRIDE threat modeling, validates exploitability, and outputs structured reports for downstream patching.
no license 168 installs ★ 129 updated 2026-10-25
npx skills add Factory-AI/factory-plugins --skill security-review -a claude-codeWhat security-review does
The skill detects SQL injection, XSS, IDOR, command injection, hardcoded secrets, and other vulnerabilities in commits, pull requests, or entire repositories. Runs in four modes: PR review before merge, weekly scan of the last seven days, full repository audit, and manual trigger via @droid security in PR comments. For each finding, it assigns a STRIDE category (spoofing, tampering, information disclosure, denial of service, elevation of privilege), pinpoints the file and line range, describes an exploit scenario, and suggests a fix. It also checks dependencies for known CVEs and evaluates whether vulnerable code paths are reachable.
Requires a .factory/threat-model.md file with a STRIDE threat model — if missing, the skill generates one automatically on first run. If the model is older than 90 days, PR mode warns and proceeds with the existing model, while weekly and full modes regenerate it before scanning. Results are saved to security-findings.json and validated-findings.json, which the security-patch-generation skill then uses to create fixes automatically.
What it helps with
- check a pull request for SQL injection, XSS, and leaked secrets
- find vulnerabilities in commits from the past week
- run a full security audit of a repository
- assess exploitability of dependency CVEs in the project
- produce a structured report for automated patch generation
Example prompts for the agent
- Check this PR for security vulnerabilities
- Scan all commits from the last seven days for SQL injection and XSS
- Run a full STRIDE security audit on the repository
How to install security-review
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill security-review -a claude-code2Manually: put the files in place
~/.claude/skills/security-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/security-review/
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill security-review -a codex2Manually: put the files in place
.agents/skills/security-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill security-review -a cursor2Manually: put the files in place
.cursor/skills/security-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Factory-AI/factory-plugins plugins/security-engineer/skills/security-review2Manually: put the files in place
.github/skills/security-review/SKILL.md1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill security-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/Factory-AI/factory-plugins --path plugins/security-engineer/skills/security-reviewManually: put the files in place
.devin/skills/security-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill security-review -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 security-review
How do I install security-review in Claude Code?
Run npx skills add Factory-AI/factory-plugins --skill security-review -a claude-code, and the skill will appear at ~/.claude/skills/security-review/SKILL.md.
What does the security-review skill do?
It scans code changes for vulnerabilities like SQL injection, XSS, IDOR, command injection, and data leaks, checks dependencies for known CVEs, evaluates whether findings are exploitable, and produces a structured report with remediation recommendations.
What does security-review need to work?
A .factory/threat-model.md file with a STRIDE threat model. If the file is missing, the skill generates it automatically on first run. You also need a Git repository with code to analyze.
Similar skills
All skills for Security →security-review by other authors comes first.