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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 4, 2026, 04:16 AM
Issues
1
Security Audit — snyk — databricks-mlflow-evaluation