video-transcript

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches transcripts and video metadata from YouTube via an external API (transcriptapi.com) based on URLs or IDs supplied by the user, but does not monitor or consume an outsider-submitted feed or queue.

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 register accounts and fetch transcripts from transcriptapi.com, an unverified third-party service, introducing an external operational dependency with weak/unknown provenance.