research-evidence
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The
research-evidenceskill’s required “Literature Search / Recent Literature / Novelty Risk Audit” workflows actively query and ingest free text (titles/authors/abstract snippets) from arXiv at runtime via the helper’s direct arXiv API calls (https://export.arxiv.org/api/queryand parsing Atom<title>/<summary>fields) based on user-supplied terms.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata