content-extractor

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

• Third-party content exposure detected (high risk: 0.85). Yes—Mode 1/2/3/4 call CF Browser MCP tools (browser_markdown, browser_json, browser_scrape, browser_links) with a user-supplied URL, which at runtime fetches public web page content and feeds the extracted free text/markup into the agent’s LLM context (indirect prompt injection risk).