polymarket-scanner

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly fetches live, user-generated market content from Polymarket's public Gamma and CLOB APIs (see SKILL.md and scripts/scan_markets.py which call https://gamma-api.polymarket.com and scripts/get_prices.py / get_orderbook.py which call https://clob.polymarket.com), and that untrusted question/outcome text is read, filtered, and used to drive further actions (resolving slugs to token IDs and fetching prices/orderbooks), so third-party content could materially influence agent behavior.