piiiico/a2a-trust-audit

A2Acommunity
piiiicoMITUpdated 4mo agoGitHub

Audit A2A agent cards across L1-L4 trust dimensions. Score your agent card. AgentLair is the L4 reference implementation.

Score any A2A agent card on identity, authentication, authorization, and behavioral trust. Zero install. One npx away. Embed a live trust grade in your README: Encode your card URL: Paste the output into the badge URL. It re-audits hourly — your grade stays current without any CI. The A2A protocol tells agents how to talk. It doesn't tell them how to trust. Most agent cards score 0% on behavioral…

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
4mo agoLast update
Package
Authorpiiiico
LicenseMIT
Sourcegithub
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/30
→ Publisher: run `forge publish` from the repo to claim ownership
—Domain verification+0/10
→ Not currently available for this listing type — the domain-verification check only runs for npm-backed packages today, so this row cannot be earned here yet regardless of what's hosted at the domain.
✓Prompt-injection scan · clean+30/30
✓Obfuscation / exfil scan · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface—
Security scan✓ CleanvHEAD · 3mo agoHow well does this scan work?
EvalsNone
IndexedJun 13, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

No tool declarations found in the source3mo ago

Forge read 1 source file 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”.

About

Score any A2A agent card on identity, authentication, authorization, and behavioral trust. Zero install. One npx away. Embed a live trust grade in your README: Encode your card URL: Paste the output into the badge URL. It re-audits hourly — your grade stays current without any CI. The A2A protocol tells agents how to talk. It doesn't tell them how to trust. Most agent cards score 0% on behavioral trust (L4). The spec has no standard for it. This tool makes that gap visible, layer by layer, in…

Keywords
a2aagent-identityagent-trustagentlairauditclidideddsajwkstrustx402
Alternatives
Comparing tool surfaces…

No dependency coverage

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.