polars
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's Data I/O documentation shows it reads arbitrary user/third‑party data sources (e.g., CSV/JSON/Parquet and connectors to S3, Azure, GCS and Google BigQuery), meaning the agent can ingest untrusted external content that could carry indirect prompt injection.
Audit Metadata