braintrust-define-eval-release-gate
Warn
Audited by Snyk on Aug 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow is to create/apply release gates by reading experiment/scorer/traces results (which may include model outputs and other text), and the provided interaction-contract explicitly warns that traces/logs can contain directive-like free text that the judge/LLM reads to gate promotion.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata