paper-select-journal
Warn
Audited by Snyk on May 1, 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 explicitly instructs runtime web verification and ingestion of open third‑party content—e.g., fetch_pubmed_recent.py calls NCBI E-utilities to pull PubMed articles and SKILL.md requires “联网核验” of journal official websites / Aims & Scope and publisher pages—and those fetched/public pages and abstracts are read by the host model to decide Set2/Set3 and final recommendations, so untrusted third‑party content can directly influence decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata