markets
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection vulnerability surface.
- Ingestion points: Untrusted market data (titles and descriptions) is retrieved from external platforms like Polymarket and Manifold via the feed manager in
index.ts. - Boundary markers: The skill does not use delimiters or boundary markers to encapsulate external content, making it possible for embedded instructions to influence the agent.
- Capability inventory: The skill itself is restricted to returning data strings to the agent, but the overall risk depends on the broader capabilities of the agent interpreting this data.
- Sanitization: No sanitization or filtering of external market content is observed in the provided code.
Audit Metadata