yt

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

• Third-party content exposure detected (low risk: 0.10). The agent retrieves outsider-authored YouTube video transcripts, titles, descriptions, and search results via api.transcriptout.com based on user or search queries.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes API calls to an external third-party service (transcriptout.com) for its core functionality, constituting a common unofficial operational dependency.