AI & Agents

Agent Passport

Last updated 2026-06-30 · benchmark checked 2026-08-09 · unchanged since 2026-08-08 — deterministic & reproducible

Authorization layer for AI agents with scoped permissions and spend limits.

Is Agent Passport production-ready?

Legit.Show scores Agent Passport 67 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Agent Passport (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 91/100
• Accessibility — 88/100
• Security — 45/100
• Privacy — 25/100
• Reliability — 100/100
• Standards — 85/100
• Discoverability — 35/100

What we measured

• Security headers present: HSTS.
• No Content-Security-Policy.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 78 ms to first byte.
• Returns a proper 404 for unknown routes.
• 2 of 2 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

AI agent developers · Enterprise teams · SaaS platforms · API providers · DevOps engineers

Pricing

Open source MIT licensed, self-hosted

Visit Agent Passport → · Alternatives to Agent Passport → · How this was measured →