weathermap-automation

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs the agent to query an external MCP server (https://rube.app/mcp) using RUBE_SEARCH_TOOLS to retrieve tool slugs, input schemas and recommended execution plans — untrusted third-party content the agent must read and that can directly change tool selection and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and calling the Rube MCP server (https://rube.app/mcp) at runtime: RUBE_SEARCH_TOOLS fetches tool schemas and recommended execution plans from that endpoint and RUBE_MULTI_EXECUTE_TOOL runs remote tools, so external content can directly control prompts/instructions and execute actions.