academic-research

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's Search Strategy explicitly directs the agent to perform web searches and ingest content from public third‑party sites (e.g., site:semanticscholar.org, arxiv.org, philpapers.org, ncbi.nlm.nih.gov) and to follow citations, so the agent will fetch and read open web content that could contain indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 11:11 AM