qinyan-citation
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). At runtime the required workflow calls
scripts/search.sh, which POSTs the user’s query tohttps://api.qinyanai.com/v1/paper-search/<source>and then prints the returned paper metadata JSON; that fetched third-party content (from Google Scholar/Wanfang/PubMed/arXiv via the Qinyan API) is outsider-authored and becomes LLM-readable text when the agent ingests the script output for citation formatting.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata