project-bubble-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill requires calling RUBE_SEARCH_TOOLS against an external Rube MCP server (https://rube.app/mcp) to fetch tool schemas and recommended execution plans that the agent must read and use to choose tool slugs/arguments and execution steps, so untrusted third-party responses can directly influence behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires contacting the Rube MCP endpoint at https://rube.app/mcp at runtime to fetch tool schemas and recommended execution plans (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS), and those fetched artifacts directly determine the agent's tool invocations and instructions.