cloudflare-mcp-server

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

• Third-party content exposure detected (high risk: 0.70). The skill includes examples and handlers that fetch and return open web or user-generated content (for example the "API Proxy MCP Server" that fetches Wikipedia in references/stateful-servers.md and the OAuth proxy/context code that uses Octokit or a generic userinfo fetch in references/authentication.md and references/oauth-providers.md), so an agent running these tools would ingest untrusted third‑party content that could carry indirect prompt-injection.