journal-abbrev
Warn
Audited by Snyk on May 19, 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 explicitly downloads and queries public third‑party sources — JabRef CSVs from raw.githubusercontent.com, AbbrevISO (abbreviso.toolforge.org), and the NLM Entrez eutils API (eutils.ncbi.nlm.nih.gov) as shown in SKILL.md and jabbrv.py — and it directly uses those responses to decide lookups and to modify .bib files, so untrusted web content can influence tool behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata