malloy-analysis

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

• Third-party content exposure detected (low risk: 0.10). The workflow only ingests the user’s plain-English question via get_context/Malloy entity discovery and then runs Malloy model queries via execute_query, but it does not describe reading any outsider-authored external feed (e.g., email/chat/tickets/GitHub/issues) or arbitrary web content at runtime.