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 instructs the agent to fetch and read public web resources (e.g., using WebFetch to load https://modelcontextprotocol.io/llms-full.txt and raw GitHub URLs like https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md, and to "use web search and the WebFetch tool as needed" to read API docs), which are open/public third-party sources the agent will ingest and interpret.