deepseek-usage
Warn
Audited by Snyk on Aug 14, 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). SKILL.md 的查询流程会在运行时 navigate 到 https://platform.deepseek.com/usage 后,在 execute_js 中读取并解析由该页面导出的 CSV(通过下载 zip 并 zip.file(...).async('text')),而这些 CSV 文本内容属于外部/用户可影响的数据源,属于间接提示注入暴露面。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill dynamically injects and executes remote JavaScript at runtime by loading https://cdnjs.cloudflare.com/ajax/libs/jszip/3.10.1/jszip.min.js into the page (script.src in execute_js), which is a required runtime dependency that executes code.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata