braintrust-monitor-production-evals
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 “braintrust-monitor-production-evals” ingests outsider-authored free text indirectly via production trace content (user turns and system/tool outputs) when online scoring evaluates live traffic and closes the loop by sampling flagged traces for review and dataset append.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata