jimeng-api-image-gen

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

• Third-party content exposure detected (high risk: 0.80). The skill's CLI and workflow explicitly accept arbitrary input image URLs (see scripts/generate_image.py --images and payload["image_urls"] as well as SKILL.md examples), which are fetched/ingested and used by the Jimeng API to influence generation results, so untrusted third-party content could indirectly alter model behavior.