academic-research

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). This skill explicitly searches, downloads, and analyzes papers and PDFs from public third-party sources (arXiv, PubMed, Semantic Scholar, bioRxiv, medRxiv, Google Scholar, etc.), so the agent will ingest untrusted external web content that could contain embedded instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:16 PM