video-transcript

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md shows it calls TranscriptAPI.com's GET /api/v2/youtube/transcript to fetch and ingest YouTube video transcripts (user-generated public content) which the agent is expected to read and act on (e.g., summarize or make decisions), exposing it to untrusted third-party content that could contain indirect prompt-injection.