image-studio
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). 该技能在 Step 5/提示词组装中直接将“用户输入的标题/要点/节点/数据等”拼入
/tmp/image-studio-prompt.txt并通过scripts/generate_image.py里的generate_image_labnana()把该 prompt 作为请求体发送给 LabNana 生成图片，从而让外部可控的自由文本进入运行时 LLM（图片生成）提示。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata