gpt-image-2-background-replace

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

• Third-party content exposure detected (medium risk: 0.30). The runtime ingests outsider-authored free text via the --prompt CLI argument on imagegen.py generate, which is sent as the prompt field in the POST /openapi/v1/generation/image request (and no server-side item selection gates it beyond requiring user-provided text).