building-mcp-server-on-cloudflare

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly shows server tools that fetch and ingest public third-party data (e.g., the get_weather tool using fetch('https://api.weather.com/${city}') and guidance about proxying to third-party APIs like GitHub), so the agent will read/interprete untrusted external content.