mcp-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to use WebFetch to load external public documents (e.g., "https://modelcontextprotocol.io/llms-full.txt" and raw.githubusercontent.com SDK READMEs) as required research steps, meaning the agent will read and act on untrusted third-party content that can influence tool design and behavior.