gatherup-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill directs the agent to call an external MCP server (e.g., RUBE_SEARCH_TOOLS against https://rube.app/mcp) to fetch tool schemas and execution plans from a third-party service, which the agent must read and interpret at runtime and thus could contain untrusted or user-controlled content enabling indirect prompt injection.