vulnerability-validation — Claude Code skill for vulnerability checks
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.
no license 135 installs ★ 129 updated 2026-10-25
npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -a claude-codeWhat vulnerability-validation does
The skill traces whether a vulnerable code path can be reached and whether an attacker controls the data that reaches it. It also checks existing safeguards and rates the effort needed to exploit a finding.
For confirmed issues, it builds a benign proof of concept with a request and expected behavior, assigns a status, and calculates a CVSS 3.1 score. Analysis requires .factory/threat-model.md from threat-model-generation and security-findings.json from commit-security-scan; it cannot start without both files.
What it helps with
- filter false alarms in security scan results
- trace whether vulnerable code is reachable
- rate the conditions needed to exploit a finding
- create a benign PoC for a confirmed issue
- calculate a CVSS 3.1 score
Example prompts for the agent
- Check the findings in
security-findings.jsonand create PoCs for confirmed issues. - Trace the reachable path and exploitation conditions for a high-severity finding.
- Assess selected finding IDs from
security-findings.jsonand calculate their CVSS 3.1 scores.
How to install vulnerability-validation
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -a claude-code2Manually: put the files in place
~/.claude/skills/vulnerability-validation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vulnerability-validation/
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -a codex2Manually: put the files in place
.agents/skills/vulnerability-validation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -a cursor2Manually: put the files in place
.cursor/skills/vulnerability-validation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Factory-AI/factory-plugins plugins/security-engineer/skills/vulnerability-validation2Manually: put the files in place
.github/skills/vulnerability-validation/SKILL.md1Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -a gemini-cli2Platform CLI
gemini skills install https://github.com/Factory-AI/factory-plugins --path plugins/security-engineer/skills/vulnerability-validationManually: put the files in place
.devin/skills/vulnerability-validation/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -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 vulnerability-validation
How do I install vulnerability-validation in Claude Code?
Run npx skills add Factory-AI/factory-plugins --skill vulnerability-validation -a claude-code. The skill file is at ~/.claude/skills/vulnerability-validation/SKILL.md.
What does vulnerability-validation do?
It checks whether reported security issues can be exploited in the codebase and removes false alarms. For confirmed issues, it produces a benign PoC and calculates a CVSS 3.1 score.
What does vulnerability-validation need to run?
It needs .factory/threat-model.md, produced by threat-model-generation, and security-findings.json, produced by commit-security-scan.