evaluate-with-braintrust
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill serves its stated purpose as an informational resource for LLM evaluation workflows.
- [COMMAND_EXECUTION]: The skill includes shell commands in the documentation for manual installation into local IDE directories (e.g.,
~/.cursor/skills/). These are standard file operations for local setup and are not executed automatically or without user action. - [EXTERNAL_DOWNLOADS]: References external resources including a YouTube playlist and the author's public GitHub repository for source material. These references are static links for documentation purposes and do not involve automated remote code execution or untrusted downloads.
Audit Metadata