mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly tells the agent to fetch and read public web content (e.g., WebFetch of https://modelcontextprotocol.io/llms-full.txt and raw.githubusercontent.com READMEs, and to "use web search and the WebFetch tool as needed"), so the agent will ingest untrusted, third-party (including user-generated) web content as part of its workflow.