database-access
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow queries and downloads public bioinformatics resources (e.g., NCBI Entrez via
requests.gettoeutils.ncbi.nlm.nih.gov), so the LLM context can ingest outsider-authored free text from fetched web/API responses (public pages/records) as readable metadata/content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata