mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and read external, public web resources (e.g., "https://modelcontextprotocol.io/llms-full.txt", raw.githubusercontent.com SDK READMEs, and other sites via WebFetch/web search), which are untrusted third-party sources the agent will read and interpret as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs the agent at runtime to WebFetch and load external specification/docs—https://modelcontextprotocol.io/llms-full.txt and the two raw GitHub READMEs (https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md and https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md)—which would be injected into the agent's context and thus directly control prompts/instructions as required runtime dependencies.