web-scraper

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow fetches outsider-authored web pages (URLs provided by the operating user) via requests/BeautifulSoup and/or playwright (fetch_static → resp.text/soup, and fetch_with_playwright → page.content()/innerText), then passes the extracted text into the agent’s LLM context in Stage 5 (optional) for entity extraction.