analyzing-research-papers
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and resolves DOIs and arbitrary URLs (e.g., arXiv PDFs, journal websites, bioRxiv/medRxiv and direct HTML/PDF links) and instructs the agent to read and analyze those public third-party documents, exposing it to untrusted user-generated or external web content that could carry indirect prompt injection.
Audit Metadata