route-engineering-work

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

• Third-party content exposure detected (medium risk: 0.30). The stateless required workflow reads outsider-authored free text from the caller-provided --request/--request-file input and passes it into the router classifier (scripts/route_engineering_work.py → validated_inputs() → route_request() → normalize_request(request)).