citation-verification
Warn
Audited by Snyk on Mar 6, 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 SKILL.md explicitly requires using WebSearch and Google Scholar for verification (and the references/api-usage.md plus scripts show runtime use of public APIs like CrossRef, arXiv, and Semantic Scholar), so the agent fetches and ingests open, third‑party web/API content which it is expected to read and use to make citation decisions.
Audit Metadata