iopho-getting-videos

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly instructs the agent to fetch and ingest content from arbitrary public video URLs (e.g., yt-dlp commands, "transcript-only" using youtube-transcript-api, and routing logic for "Any other URL" covering 1800+ sites including YouTube/Bilibili/Vimeo), so untrusted, user-generated third-party content (videos/subtitles/metadata) will be read and can materially influence downstream decisions.