enigma-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill requires calling RUBE_SEARCH_TOOLS against the Rube MCP endpoint (https://rube.app/mcp) to fetch live tool schemas, "recommended execution plans," and other runtime data which the agent is expected to read and use to decide and execute tools, so untrusted third-party content can directly influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding the MCP server https://rube.app/mcp and explicitly calls RUBE_SEARCH_TOOLS (which returns tool schemas and recommended execution plans that directly control agent instructions) and RUBE_MULTI_EXECUTE_TOOL (which runs tools remotely), so the rube.app/mcp endpoint is a runtime dependency that can control prompts and execute code.