analyzing-research-papers

Warn

Audited by Snyk on Feb 24, 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's "Paper Access Methods" explicitly instructs ingesting content from DOIs and URLs (e.g., arXiv, journal websites, bioRxiv/medRxiv and resolving via https://doi.org/{doi}), and the workflow requires the agent to read and analyze those public third-party PDFs/HTMLs, so untrusted external content can directly influence its decisions and outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 12:27 PM