braintrust-tracing

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily documentation and a configuration guide for a third-party tracing integration. It does not contain executable code blocks that would automate malicious actions.
  • [COMMAND_EXECUTION]: The skill lists standard shell commands (e.g., tail, cat, jq) and manual execution steps for local scripts (e.g., bash, python) intended for developer debugging and system verification.
  • [DATA_EXFILTRATION]: Documents the intentional transmission of tracing telemetry to api.braintrust.dev. Braintrust is a well-known service for AI model observability and evaluation.
  • [CREDENTIALS_UNSAFE]: References the BRAINTRUST_API_KEY environment variable. The guide demonstrates best practices by checking for the variable's presence rather than hardcoding or exposing sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 09:03 AM
Security Audit — agent-trust-hub — braintrust-tracing