qinyan-topic-analysis
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). SKILL.md and scripts/search.sh explicitly require fetching and ingesting literature from public third‑party sources (Google Scholar, ArXiv, PubMed, Wanfang) via the QINYAN OpenAPI (https://api.qinyanai.com/v1/paper-search/{source}), and those retrieved untrusted/public documents are read and analyzed to drive topic-generation decisions, which could enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata