prediction-markets-research

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries public prediction markets (Polymarket, Kalshi, Metaculus) via an API, meaning market questions and titles can contain outsider-authored text, but the agent must actively search or fetch specific items.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes runtime HTTP requests to the third-party Crawlora API endpoint (api.crawlora.net), which constitutes an operational dependency with common or reputable unofficial provenance.