graph-learning-papers-guide
Warn
Audited by Snyk on Apr 2, 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.md "Paper Search" section includes executable code (arxiv.Search in the Paper Search snippet) that fetches public arXiv papers and the guide's stated use cases (literature survey / research planning) indicate the agent would read and act on that untrusted third-party content, so external paper text could indirectly inject instructions affecting decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata