agent-lookup
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches agent registry data from the vendor's official API at https://aibtc.com/api/agents to provide lookup and statistics functionality.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted metadata from an external source.
- Ingestion points: The skill fetches agent names and descriptions from the external API at https://aibtc.com/api/agents in the fetchAllAgents function.
- Boundary markers: Absent. No prompt-level delimiters or instructions are provided to the agent to treat the fetched registry content as untrusted data.
- Capability inventory: Although the skill itself is read-only, the agent using it may have access to other tools with the ability to perform transactions or modify files, making the injection of malicious instructions a risk.
- Sanitization: Absent. The implementation does not filter or sanitize the strings retrieved from the API (e.g., displayName, description) before they enter the agent's context.
Audit Metadata