moonpay-prediction-market
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted market data from external sources like Polymarket and Kalshi through commands like
market searchandevent retrieve. This ingestion occurs in an environment where the agent also has access to sensitive capabilities, including wallet management and trade execution via the MoonPay CLI. - Ingestion points: Market search results, event details, and trending market lists retrieved from external providers.
- Capability inventory: Wallet creation/listing (
mp wallet), authentication (mp login), and trade execution (mp position buy/sell). - Boundary markers: None explicitly defined in the skill instructions to delimit untrusted content.
- Sanitization: No evidence of data validation or sanitization before the external content is processed by the agent.
Audit Metadata