paper-research
Warn
Audited by Snyk on Apr 28, 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.md explicitly instructs the agent to query and fetch public academic sources (arXiv, Google Scholar, Semantic Scholar, etc.) using tools like
web_searchandweb_fetchand to read/interpret abstracts and paper pages as part of analysis, so untrusted third‑party content can directly influence decisions and report generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata