yt

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches YouTube transcripts and search results from TranscriptAPI, which contain user-generated content and comments from third parties on YouTube videos.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to make runtime API calls to transcriptapi.com and execute automated registration flows against its endpoints, but transcriptapi.com represents an unverified third-party service lacking established first-party enterprise provenance.