braintrust-design-eval-metric-bundle

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 for creating/auditing metric bundles and explicitly references reading “traces, logs, model outputs, and dataset rows” as evidence, which are user-supplied/outside-system text that can contain instruction-like content (prompt injection/directive-following), so outsider-authored free text can be ingested via the evaluation artifacts.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 20, 2026, 10:16 PM
Issues
1