building-mcp-server-on-cloudflare

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

• Third-party content exposure detected (high risk: 0.90). The skill's code and docs explicitly show the MCP server fetching and ingesting open third-party content (e.g., the get_weather tool calling https://api.weather.com/${city} in SKILL.md and the OAuth proxying to GitHub/other providers in references/oauth-setup.md), so untrusted external/user-controlled content is read and can materially influence tool behavior.