Audit your A2A agent card across L1-L4 trust dimensions on every PR. GitHub Action wrapping @agentlair/a2a-trust-audit.
Audit your A2A agent card across L1–L4 trust dimensions on every PR. Catches the moment your card silently regresses from B to F. Embed a live trust grade in your README — no CI required: Encode your card URL: Paste the output into the badge URL. The badge re-audits hourly. The A2A protocol has standards for identity (L1) and authorization (L3). It has nothing for behavioral trust (L4). This…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Forge read 2 source files from the repository archive and matched no MCP tool registrations. Extraction is pattern-based over shipped source: a server that builds its tool list at runtime, or that ships only bundled or minified code, registers nothing this can see. Treat it as “not detected”, not as “exposes none”.
Audit your A2A agent card across L1–L4 trust dimensions on every PR. Catches the moment your card silently regresses from B to F. Embed a live trust grade in your README — no CI required: Encode your card URL: Paste the output into the badge URL. The badge re-audits hourly. The A2A protocol has standards for identity (L1) and authorization (L3). It has nothing for behavioral trust (L4). This action grades your card on all four layers — including the one nobody else checks — and posts the result…
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.