reply-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 the external Rube MCP endpoint (https://rube.app/mcp) to fetch tool schemas and recommended execution plans that the agent must read and use to determine tool arguments and execution, so untrusted third-party responses could materially change agent 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 and querying the MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS), and those fetched tool schemas and execution plans directly determine the agent's prompts and actions, so this remote endpoint can control the agent's behavior.