datadata-dql
Warn
Audited by Snyk on Jul 3, 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 的运行时工作流程包含
fetch()获取外部 HTTP 响应体(可能为任意文本/HTML/XML/纯文本),其response.body会被解析为可读字符串并进入后续 LLM 上下文(例如用户/脚本将其return或用于构造结果)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata