braintrust-eval

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 (low risk: 0.10). In SKILL.md Phase 3 the agent reads and inspects outsider-authored free text from Hugging Face dataset content via the dataset viewer REST API (e.g., /first-rows and related metadata), before proposing and importing candidate datasets into the eval.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 20, 2026, 10:17 PM
Issues
1