oce-mcp-integration

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

• Third-party content exposure detected (low risk: 0.10). The MCP runtime workflow ingests assistant-invoked tool inputs (e.g., search_cost_items accepts user-provided q and forwards it to GET /api/v1/costs/?region=...&q=..., and other tools accept free-text/BIM element descriptions) but it is not described as monitoring arbitrary outsider-submitted sources like email/chat/queues or reading external issue/support text.