youtube-to-blog-post

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly fetches YouTube transcripts and uses google_search and scrape_page on arbitrary URLs (e.g., "get_youtube_transcript", "google_search", "scrape_page" in the Workflow/Output Strategy) and then instructs the agent to read/interpret those transcripts and pages to draft and verify a blog post, exposing the agent to untrusted, user-generated third‑party content that could contain indirect prompt injections.