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.py uses DuckDB to read outsider-authored dataset content from Hugging Face public/private repos via the hf://datasets/... path (e.g., query()/describe() build hf://.../*.parquet and execute SELECT * 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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 20, 2026, 09:25 PM
Issues
1
Security Audit — snyk — hugging-face-datasets