anysite-audience-analysis

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests and analyzes public, user-generated social media content (e.g., follower bios and comments via get_instagram_user_friendships and get_instagram_post_comments, YouTube comments via get_youtube_video_comments, and LinkedIn posts via get_linkedin_user_posts), which are untrusted third‑party sources the agent reads and interprets.