webscrapingai

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

• Third-party content exposure detected (high risk: 0.80). The skill integrates with WebScraping.AI and instructs using Membrane actions and the proxy (e.g., "Scrape" functionality and "membrane request CONNECTION_ID /path/to/endpoint") to fetch and ingest data from public websites, so the agent will read untrusted third‑party web content that can materially influence subsequent actions.