braintrust-tracing

Warn

Audited by Snyk on Mar 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs querying the Braintrust API (default BRAINTRUST_API_URL=https://api.braintrust.dev) via scripts/braintrust_analyze.py to fetch session traces and tool_input.prompt/tool_output (user-generated session content), and the guide describes reading and correlating that content to drive tracing and linking decisions, so the agent will ingest untrusted third-party session data.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 23, 2026, 09:03 AM
Issues
1
Security Audit — snyk — braintrust-tracing