prediction-markets
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with the official APIs of Polymarket, Kalshi, and Manifold Markets to fetch market data and event information.
- [PROMPT_INJECTION]: The skill processes untrusted data from prediction market APIs, creating an indirect prompt injection surface where malicious content could influence the agent.
- Ingestion points: Data is fetched through API endpoints defined in
SKILL.md(e.g.,get_active_markets,get_events, andsearch_markets). - Boundary markers: No delimiters or safety instructions are used to isolate untrusted data in the provided code snippets.
- Capability inventory: The skill uses the
requestslibrary to perform network operations, including reading market data and placing orders. - Sanitization: No sanitization or validation of external API data is performed before it is processed by the agent.
Audit Metadata