mcp

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

• Third-party content exposure detected (high risk: 0.90). The skill includes examples that fetch and ingest arbitrary web content (e.g., the fetch_url tool in "Lifespan Management" calling ctx.lifespan.http_client.get(url) and the "API Integration Server" using httpx to call external endpoints), and those fetched results are returned into the MCP client / Claude message loop (see "Building MCP Clients" process_query), meaning untrusted third‑party content can directly influence subsequent tool use and decisions.