bench-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the external Rube MCP endpoint (https://rube.app/mcp) and ingest returned tool schemas, tool slugs, and recommended execution plans from that public third‑party service, meaning it reads and interprets untrusted external content as part of its workflow.