ux-review
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill includes management scripts such as setup.sh and sync.sh that execute standard file system commands like ln, cp, mv, and mkdir to organize agent skills and update AGENTS.md metadata markers.
- [EXTERNAL_DOWNLOADS]: Assets and documentation reference official container images, well-known GitHub Actions, and popular developer CLI tools like k6 and Bruno CLI, all of which are sourced from trusted registries and official repositories.
- [SAFE]: The project demonstrates a strong security posture by providing explicit guidance on secret management in Terraform and implementing environment-based configuration best practices, with no evidence of prompt injection or data exfiltration.
Audit Metadata