AI & Agents

VulnClaw

Last updated 2026-07-27 · benchmark measured 2026-08-09 — deterministic & reproducible

VulnClaw is an open-source, AI-driven penetration testing CLI tool for Python 3.10+.

Is VulnClaw production-ready?

Legit.Show scores VulnClaw 66 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on VulnClaw (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Standards; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 62/100
• Accessibility — 85/100
• Security — 45/100
• Privacy — 25/100
• Reliability — 80/100
• Standards — 92/100
• Discoverability — 75/100

What we measured

• Security headers present: HSTS.
• No Content-Security-Policy.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 240 ms to first byte.
• Returns a proper 404 for unknown routes.
• 1 of 3 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

Security researchers · Penetration testers · CTF participants · Security engineers · DevSecOps teams

Pricing

Open source, MIT License

Visit VulnClaw → · Alternatives to VulnClaw → · How this was measured →