fine-tuning-expert
Warn
Audited by Snyk on Oct 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow guides the agent to read and validate training datasets (such as JSONL/CSV files provided by users or pipelines) that contain free-text instruction-response pairs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata