emelia-automation

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

• Third-party content exposure detected (high risk: 0.70). The skill requires calling RUBE_SEARCH_TOOLS against an external MCP endpoint (e.g., https://rube.app/mcp) to fetch tool schemas/recommended execution plans and then uses those returned schemas to choose and execute tools, so third-party content from that service can directly influence agent 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 using the MCP server https://rube.app/mcp at runtime to perform RUBE_SEARCH_TOOLS/RUBE_MANAGE_CONNECTIONS calls that return tool schemas and execution plans which directly control the agent's prompts and actions.