trt-perf-analysis

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow ingests outsider-authored free text only from user-supplied input JSON files in a chosen folder (e.g., layers_*.json/profile_*.json), and there is no separate feed/queue/web-fetch where an outsider can POST/push arbitrary text for ingestion without providing the JSON files themselves.