youtube

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches public, user-generated YouTube content (search results, playlistItems/video titles & descriptions via the data proxy and full video transcripts via the youtube-transcript-api) as required by the SKILL.md workflows, so the agent will read and act on untrusted third-party content that could contain instructions.