youtube-api

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches YouTube transcripts and search/channel/playlist data from the public TranscriptAPI service (see SKILL.md endpoints like https://transcriptapi.com/api/v2/youtube/transcript and /search) — these are untrusted, user-generated/public web contents that the agent is expected to read and interpret (see scripts using httpRequest/fetch to those endpoints), so third-party content could contain instructions that materially influence the agent's actions.