my-fetch-youtube

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests public YouTube subtitles/metadata via yt-dlp ("자막 추출", "메타데이터 추출" sections) and then runs Web Search on extracted keywords to correct captions ("Web Search 보정" section), meaning untrusted third-party content is read and used to change downstream corrections, summaries, and actions.