lamindb
Warn
Audited by Snyk on Feb 15, 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's Integrations and Ontologies sections (e.g., "HTTP/HTTPS endpoints (read-only)", "HuggingFace datasets", and bt.CellType.import_source()) show it can fetch and ingest data from public third‑party sources, so the agent may read and act on untrusted, user‑provided web/ dataset content during normal workflows.
Audit Metadata