troubleshoot-mcp-connection

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (SKILL.md Step 2 and Step 4) instructs using mcp-remote to connect to a public Hugging Face MCP endpoint (https://huggingface.co/mcp), running curl against huggingface.co, and searching GitHub issues — all public, user-generated sources whose responses (including MCP tool registrations and issue content) the agent is expected to read and that can materially influence tool registration and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes mcp-remote with the URL https://huggingface.co/mcp at runtime to connect to a remote MCP server which registers tools and can execute remote tool code, meaning the fetched server content can directly control agent behavior and run code.