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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 22, 2026, 06:00 AM
Issues
1