polymarket

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). Outsider source: the skill fetches public market data at runtime from Polymarket’s public gamma API (e.g., https://gamma-api.polymarket.com/markets?...), and the LLM would ingest the returned JSON fields like question (free-text market prompts) as part of the workflow’s extracted text.