gpt-image-2-product-image

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

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is accepted directly as the CLI --prompt argument in skill_generate()/cmd_image() and is then sent as the prompt field to POST .../generation/image via AiHiveClient.generate_image() (runtime ingestion by the LLM occurs downstream of this request).