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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 19, 2026, 07:15 AM
Issues
1