clean-content-fetch
Warn
Audited by Snyk on May 29, 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). 该技能在运行时接收用户提供的
<url>并通过scrapling/curl_cffi/playwright抓取网页正文,再用html2text将网页 HTML/正文提取为可读 Markdown 文本进入 LLM 上下文,因此可能包含“公共网页/任意 URL 的外部正文”这类 outsider free text。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata