proxiedmail-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 (https://rube.app/mcp) to retrieve tool schemas and recommended execution plans which the agent must read and use to drive RUBE_MULTI_EXECUTE_TOOL calls, allowing untrusted third-party content to materially influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires using https://rube.app/mcp as the MCP server and calls RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS at runtime to fetch tool schemas and recommended execution plans from that endpoint, which directly determine agent prompts and executions, so this external URL is a runtime dependency that can control the agent.