youtube-to-blog-post

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

• Third-party content exposure detected (high risk: 1.00). The skill directly fetches and ingests arbitrary public YouTube content (via get_video_info() using yt-dlp from the provided URL) and then reads/interprets the video description/tags in generate_article_content(), generate_faq_section(), generate_seo_keywords() and generate_related_posts_section() to drive metadata, content generation and linking, so untrusted third‑party text can materially influence behavior and act like an indirect prompt injection source.