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