prediction-market-data
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external prediction markets (Polymarket and Kalshi), which includes user-generated market titles and metadata that could potentially contain hidden instructions.
- Ingestion points: The
scripts/prediction_market_client.pyscript fetches market data from theapi.aisa.oneendpoint. - Boundary markers: The skill does not implement delimiters or safety instructions when passing retrieved market data to the agent context.
- Capability inventory: The skill has network access capabilities via Python's
urlliblibrary to communicate with the AIsa API. - Sanitization: No sanitization or filtering is performed on the market content before it is returned to the agent in JSON format.
Audit Metadata