hugging-face-datasets
Warn
Audited by Snyk on Jun 20, 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 required runtime workflow for
scripts/sql_manager.pyuses DuckDB to read outsider-authored dataset content from Hugging Face public/private repos via thehf://datasets/...path (e.g.,query()/describe()buildhf://.../*.parquetand executeSELECT * FROM '{hf_path}'), so arbitrary text fields from those datasets can be ingested into the agent’s LLM context through returned query results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata