yandex-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to call RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS against the external Rube MCP endpoint (https://rube.app/mcp) to fetch tool schemas and recommended execution plans, i.e., third-party content the agent must read and act on, which could be untrusted and enable indirect prompt injection.