scrapesocial-instagram

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and analyze user-generated Instagram content (posts, reels, comments, transcripts) via the Scrape Creators API (see SKILL.md and references/instagram-command-map.md commands like instagram posts get, instagram comments, instagram reels search), which exposes it to untrusted third‑party content that could contain indirect prompt injections.