braintrust-deploy-evaluator

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 workflow for “braintrust-deploy-evaluator” can run an LLM evaluator over production traces/logs during activation/rewind/backfill, and those trace/log texts are derived from the evaluated system’s interactions (including user turns) that may contain attacker-controlled instruction-like content, creating an indirect prompt-injection exposure path.

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