gpt-image-2-image-to-image

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

• Third-party content exposure detected (low risk: 0.10). The runtime workflow ingests only outsider-authored free text provided to the skill at call-time via the user’s --prompt argument, which is then sent to the AI Hive POST /openapi/v1/generation/image endpoint as the prompt field (no queue/feed/monitoring of arbitrary outsider text is performed).