cloudflare-mcp-server

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

• Third-party content exposure detected (high risk: 0.80). The skill includes explicit examples and templates that fetch and expose public, user-generated web content (e.g., the "API Proxy MCP Server" tool that fetches https://en.wikipedia.org, the "browser-rendering" web-scraping example, and the RAG/Vectorize templates), so the agent will ingest and read untrusted third‑party content as part of its workflow.