Real Literature Trace
Warn
Audited by Snyk on Mar 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Search workflow and International source strategy explicitly require using Google Scholar-style discovery and verifying papers on open/public third-party pages (publisher/DOI pages, CNKI, Google Scholar), so the agent will fetch and read untrusted web content and use it to drive selection and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata