aliyun-qwen-image-edit

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

• Third-party content exposure detected (high risk: 0.70). The skill's required interface and workflow (SKILL.md's image.edit request and the "image" parameter) and the helper script (scripts/prepare_edit_request.py showing an image URL) clearly accept and ingest arbitrary external image URLs/paths, so untrusted third-party content (user-provided or web-hosted images) would be read and could indirectly influence model behavior.