twitch-research

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

• Third-party content exposure detected (medium risk: 0.30). The skill queries Twitch data via the Crawlora API, including user-generated content such as VOD comments and stream titles, which are outsider-authored free text ingested at runtime.

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 Crawlora API at api.crawlora.net, which is an external operational dependency.