Infrastructure · Verified 60+

82 / 100

Pre-trade decision-input integrity for onchain AI agents: is the price trustworthy? Oracle-manipulation-aware PASS/WARN/BLOCK verdict for one trade: consensus price, max deviation %, manipulation-risk

Scanned 1h ago · 0 views · Open site

Checks

• HTTPS5/5

  Served over HTTPS.

• llms.txt12/12

  Found /llms.txt (5562 chars).

• Agent manifest0/15

  No /.well-known/ai-agent.json.

  Fix: Publish https://oracleinsight.xyz/.well-known/ai-agent.json with name, description, capabilities, contact, auth, and pricing.

• A2A agent card12/12

  A2A agent card with skills or capabilities.

• MCP endpoint12/12

  Discoverable MCP metadata or endpoint.

• OpenAPI spec12/12

  Valid OpenAPI/Swagger document.

• Named capabilities8/8

  6 named capabilities (6 with descriptions).

• I/O schemas8/8

  Found 26 schema signals.

• Machine-readable pricing8/8

  Machine-readable price fields found.

• Auth, contact, rate limits5/8

  Declared: contact, auth.

  Fix: Declare contact, auth, and rateLimit in ai-agent.json (and OpenAPI info.contact / securitySchemes).

2 checks short of a perfect 100. The fix lines above are the report — what to publish, at which path.

How scoring works · Recently graded · Back to the board