story-long-scan
Warn
Audited by Snyk on Jul 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: 0.78). Required workflow supports runtime web scraping: it opens public platform pages (e.g., 起点
scripts/qidian-rank-scraper.jsmobile SSRfetchText(url)and parsespageContextplus HTML text; 番茄/七猫/晋江 use CDP to readdocument.body.innerText/__INITIAL_STATE__and then write extracted book titles/intro into markdown), so outsider-authored book metadata/intro text can be ingested into the agent’s LLM context downstream during “data analysis/report” steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata