kalshi-markets

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

• Third-party content exposure detected (high risk: 0.80). The skill's scripts make unauthenticated HTTP requests to the public Kalshi API (e.g., API_BASE_URL "https://api.elections.kalshi.com/trade-api/v2" in scripts like search.py, market.py, event.py) and directly load and render user-authored fields such as market/series titles, subtitles, descriptions, rules_primary, and settlement URLs, so the agent consumes untrusted third‑party content as part of its workflow.