cmc-api-market
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches cryptocurrency market data and social sentiment metrics from CoinMarketCap's official API endpoints.
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest untrusted, user-generated content from the CoinMarketCap community platform, which could contain malicious prompt instructions.
- Ingestion points: Endpoints documented in
references/content.md(latest/top posts and comments) andreferences/community.md(trending tokens and topics). - Boundary markers: Absent. The skill provides no delimiters or instructions for the agent to ignore potentially malicious content embedded in the API responses.
- Capability inventory: The skill is authorized to use
Bashfor network requests viacurlandReadfor internal file access. - Sanitization: Absent. No explicit instructions are provided to the agent to validate or sanitize the text content retrieved from the community-based endpoints.
Audit Metadata