databricks-mlflow-evaluation
Warn
Audited by Snyk on Jul 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests SME free-text rationales/comments from the labeling session (outsider-authored) into MemAlign alignment, which then feeds that text into the LLM via
base_judge.align(traces=...)/ MemAlign guideline distillation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata