instagram-audience-voice

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs collecting and scraping public Instagram posts and comments (SKILL.md recommended workflow step 1: "collect comments from a shortlisted set of posts or reels", plus actor-selection references to instagram-comment-scraper and the run_instagram_actor tool contracts), which ingests untrusted, user-generated social-media content that the agent must read and summarize and which can directly influence downstream clustering, decisions, and outputs.