qlora
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: 1.00). The skill loads and uses a public, user-generated dataset via load_dataset("tatsu-lab/alpaca") (Hugging Face), so the agent ingests untrusted third-party content as part of its training workflow, which could contain injected instructions.
Audit Metadata