research-plan
Warn
Audited by Snyk on Jul 19, 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). 该 Skill 的“文献检索/下载与 PDF 信息提取”流程会在运行时读取来自外部来源(如 PubMed/Google Scholar/IEEE Xplore/arXiv/Semantic Scholar 的检索结果与下载的 PDF 文本),这些属于“公共网页/外部文档内容”并可能被拼入 LLM 上下文进行逐篇评估与语义提取。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata