intelligent-content-system
Warn
Audited by Snyk on Jul 27, 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). 运行时在“采集网页”相关工作流(如 url-to-markdown,用用户提供的URL去抓取网页并转成Markdown)会把网页正文/元数据等“公共网页内容”作为可读文本喂入LLM上下文,存在间接提示注入风险。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata