whautomate-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill mandates calling RUBE_SEARCH_TOOLS against the Rube MCP endpoint (e.g., https://rube.app/mcp) to retrieve live tool schemas, execution plans, and recommendations that the agent must read and use to decide tool selection and arguments, so untrusted third-party responses could materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime connection to Rube MCP at https://rube.app/mcp, and its RUBE_SEARCH_TOOLS responses (tool schemas and recommended execution plans) directly control the agent's instructions/executions and are a required dependency.