gpt-image-2-character-consistency

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow ingests outsider-authored free text via the user-supplied --prompt (and optional --system) parameters in cmd_image() → client.generate_image(..., prompt=args.prompt, ...), then forwards that prompt to the generation/image API endpoint.