lyt-product-image-patterns
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). 该 skill 的运行流程允许输入“1688、TikTok Shop、竞品链接或公开样本表/图片文件夹路径”,并在“建样本表/清洗样本”阶段对这些竞品主图进行识别与提取可读内容,从而把“竞品/Top 店铺主图(外部作者的图片文字与描述)”作为 LLM 上下文输入(间接提示注入风险)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata