bib-verify
Warn
Audited by Snyk on Mar 7, 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 explicitly instructs the agent to "Lookup — query CrossRef, arXiv, and DBLP for each reference," which fetches and interprets public third‑party metadata from external academic sites as part of its verification workflow, so untrusted external content can influence its decisions.
Audit Metadata