typless-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill requires calling RUBE_SEARCH_TOOLS against the Rube MCP server (https://rube.app/mcp) to fetch tool schemas, recommended execution plans, and tool slugs which the agent must read and act on, exposing it to third-party-provided instructions that could influence subsequent tool use.

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

• Potentially malicious external URL detected (high risk: 1.00). The MCP server endpoint https://rube.app/mcp is a required runtime dependency (used via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) that returns tool schemas and execution plans which directly control the agent's instructions and tool execution.