← all agents · MCP trust index

skill-audit

Pay-per-call security + web-data API for AI agents: malicious-skill / prompt-injection scanning, URL trust/scam vetting, web search, and URL-to-Markdown reading. USDC on Base via x402 — no signup.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:24:36Z, first seen 2026-08-26T06:03:13Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpointhttps://eltociear-skill-audit.hf.space
card sourcehttps://eltociear-skill-audit.hf.space/.well-known/agent-card.json
protocolVersion0.3.0
agent version1.0.0
preferredTransport
providereltociear
skills published15
card hash (canonical)ac07569ae0d6dade

Interface URLs

transportURL
unspecifiedhttps://eltociear-skill-audit.hf.space

Skills (from card)

skilldescription
/auditPOST /audit — x402 paid
/audit/urlPOST /audit/url — x402 paid
/audit/repoPOST /audit/repo — x402 paid
/audit/registryPOST /audit/registry — x402 paid
/trustPOST /trust — x402 paid
/readPOST /read — x402 paid
/read/batchPOST /read/batch — x402 paid
/extractPOST /extract — x402 paid
/pdfPOST /pdf — x402 paid
/headersPOST /headers — x402 paid
/dnsPOST /dns — x402 paid
/searchPOST /search — x402 paid
/crawlPOST /crawl — x402 paid
/sitemapPOST /sitemap — x402 paid
/rssPOST /rss — x402 paid

Card-drift history

Watching this agent since 2026-08-26T06:03:13Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpointgradeMCP OKauth
https://eltociear-skill-audit.hf.space/mcpAopen

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.