sparta-exposure

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow ingests only the user’s question text and then runs /extract-entities and evidence-case/monitor/read-model lookups, with grounding and evidence limited to service-owned structured outputs rather than outsider-published free-text sources like tickets, inboxes, or public feeds.