braintrust-analyze

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'Bash' tool to execute a local Python script 'scripts/braintrust_analyze.py' for session analysis, including token usage trends and loop detection.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its consumption of session traces from the Braintrust API. 1. Ingestion points: Session traces and span metadata from Braintrust API. 2. Boundary markers: No explicit boundary markers or 'ignore' instructions for trace data are provided in the documentation. 3. Capability inventory: The skill has access to the 'Bash' tool to execute analysis routines. 4. Sanitization: There is no evidence of sanitization or validation performed on the retrieved tracing data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 05:43 PM
Security Audit — agent-trust-hub — braintrust-analyze