technical-writing
Warn
Audited by Snyk on Jun 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). 阶段2“深度研究”会对用户提供的素材 URL 运行
web_fetch/web_search获取并提取网页/文章等正文文本,再把这些“原始来源内容/关键引言”用于后续生成文章的 LLM 上下文;该网页内容属于运行时公共网页等外部作者的自由文本。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata