transcript

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow fetches YouTube video transcripts from transcriptapi.com, where video content and metadata are authored by arbitrary third-party users.

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 via arbitrary API endpoints at transcriptapi.com, an unknown third-party service lacking strong first-party provenance, constituting a weak/unknown operational dependency.