agent-lookup
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches agent data from the API at
https://aibtc.com/api/agents, which includes fields likedisplayNameanddescription. These fields are user-controlled and could contain malicious instructions designed to subvert agent logic. - Ingestion points: Agent data is ingested via network requests in
agent-lookup.ts. - Boundary markers: The skill does not implement delimiters or safety instructions in its output to isolate untrusted data from the agent's prompt context.
- Capability inventory: The skill performs network operations via
fetchand is executed usingbun. - Sanitization: No sanitization or validation is applied to the retrieved agent metadata before it is returned as JSON.
Audit Metadata