model_finetuning

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: 0.90). The skill explicitly loads public, user-contributed datasets (e.g., load_dataset("trl-lib/Capybara"), "trl-lib/ultrafeedback_binarized", dataset_name argilla/Capybara-Preferences) and even arbitrary JSON data_files, so it ingests untrusted third-party/user-generated content as part of its training workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:56 AM