addresszen-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to call RUBE_SEARCH_TOOLS against the Rube MCP endpoint (e.g., https://rube.app/mcp) to fetch tool schemas and recommended execution plans which the agent must read and use to determine tool slugs and arguments, exposing it to arbitrary third-party content that could embed instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The Rube MCP endpoint https://rube.app/mcp is explicitly required at runtime (used by RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS / RUBE_MULTI_EXECUTE_TOOL) and returns tool schemas and execution plans that directly control which prompts/tools the agent uses and how it executes actions.