social-content

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

• Third-party content exposure detected (high risk: 1.00). The "SCRAPE — Collect Posts at Scale" section explicitly instructs gathering 500–1,000+ posts from identified creators and using scrapers (Apify, PhantomBuster, manual copy/paste) to ingest social media posts (user-generated, public third‑party content) for analysis, so the agent would read and interpret untrusted third‑party content.