data-scraper-agent
Warn
Audited by Snyk on Jun 22, 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). 该技能在运行时会通过“公共数据源抓取→将抓取到的文本/字段拼入 LLM prompt”的路径把外部内容喂给 Gemini:
scraper/main.py调用fetch_fn()获取 items(来自运行时指定的 URL/API/RSS/HTML/Playwright 页面),再由ai/pipeline.py的_build_prompt()将json.dumps(item)生成的可读文本拼入prompt,从而进入ai/client.py的generate()(LLM 上下文)。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata