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 only ingests outsider-authored text that is directly provided by the caller as the --prompt (and optional --system) CLI argument, which is then sent to the AI Hive POST /openapi/v1/generation/image via client.generate_image, with no automatic reading of external feeds/queues/content.