wenqu-image

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

• Third-party content exposure detected (medium risk: 0.30). sources/prompt exposure: 在 references/gen-workflow.md 第2/3步，技能从调用方文章中读取 > 🖼️ 待配图 占位标记与 # 画图提示 代码块正文（外部可由用户/作者提供的自由文本），并将其拼入生成用的 --prompt 交给脚本 scripts/gpt-image-2-gen.sh 进行图像生成。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's scripts (e.g., scripts/fetch-ref.sh) download style reference images at runtime from https://raw.githubusercontent.com/gogoingai/wenqu-skills/master/wenqu-image-assets/styles (and specific raw image URLs such as https://raw.githubusercontent.com/gogoingai/wenqu-skills/master/wenqu-image-assets/styles/mono-marker/mono-marker-02-branch-decision.png), which are then passed as --ref to the image-generation tool and therefore directly influence model outputs and are required for operation.