mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to fetch and read public web content (e.g., "Use WebFetch to load: https://modelcontextprotocol.io/llms-full.txt" and raw GitHub READMEs, and to "use web search and the WebFetch tool as needed"), i.e., untrusted third‑party pages that the agent is expected to interpret as part of its workflow and that could materially influence tool design and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to WebFetch external documents at runtime—e.g. https://modelcontextprotocol.io/llms-full.txt and the raw GitHub README URLs (https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md, https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md)—which would be injected into the model context and directly influence agent prompts/instructions as required runtime dependencies.