Scraping

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public third‑party content (web pages and social media) — e.g., BrightData/Workflows/FourTierScrape.md (Step 1: "Use WebFetch tool ... Extract all content from this page and convert to markdown") and Apify SKILL/INTEGRATION docs and actor wrappers that call Apify actors to return tweets, posts, Google Maps entries, Amazon reviews, etc., and then the agent is expected to read/transform that content (e.g., "Script returns: Tweet text + metadata" → "System transforms tweet into LinkedIn format"), so untrusted user-generated content can directly influence actions.