unione-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 the external Rube MCP endpoint (https://rube.app/mcp) to retrieve live tool schemas, recommended execution plans, and auth links which the agent must read and act on, exposing it to untrusted third-party content that could inject instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires connecting to the external MCP server at https://rube.app/mcp and calls RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS at runtime to fetch tool schemas and execution plans that directly drive agent prompts and tool execution, so this endpoint is a runtime dependency that controls instructions.