create-ex
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md 的运行流程要求在 Step 2/3 里读取用户上传/导出的聊天记录、社交截图文本、照片 EXIF 等,并在 Step 3/4 将这些“原材料”汇总后喂给 LLM 做分析与生成;这些原材料包含前任/他人(非操作用户)撰写的对话内容,因此属于“免费文本/消息内容(outsider-authored)经由本地文件解析后进入 LLM 上下文”的间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata