mboum-automation

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to call RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS against the external MCP endpoint (https://rube.app/mcp / Composio) to fetch tool schemas and execution plans, which are third-party, potentially untrusted content that the agent must read and act on.