story-long-scan
Warn
Audited by Snyk on Jun 26, 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脚本采集番茄/七猫/起点/晋江/刺猬猫等“公共网页”上的榜单条目与详情页简介/标签等外部作者文本,并将其作为可读 Markdown 写入 LLM 上下文(间接提示注入风险);例如
fanqie-rank-scraper.js从详情页 HTML 抽取abstract/description(简介)并写入输出文件。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata