ceae-skill
Warn
Audited by Snyk on Aug 27, 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). 该技能在运行时会把“用户输入的模糊优化目标/参数化目标”生成因果树JSON并在 scripts/ceae_tree_export.py 中读取该 JSON 的 label/id 文本用于生成 PNG(通过 _parse/ax.text 渲染),因此外部可提交的自由文本会直接进入 LLM 生成的可读节点文本并被后续流程消费。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata