HuggingFace Model Trainer

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly loads and trains on external Hugging Face datasets (e.g., dataset = load_dataset("your-org/your-dataset", split="train") and dataset.push_to_hub) so untrusted/public user-provided content from the Hub can be ingested and materially influence training and subsequent agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 12:57 PM