running-with-without-evals
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation and procedural guides for internal testing and evaluation workflows. It does not contain any executable code, remote downloads, or malicious patterns.
- [COMMAND_EXECUTION]: The instructions describe how to run a local shell script (
run-arm.sh) located within the project's own directory structure. This is a standard development task and does not involve untrusted remote sources. - [DATA_EXPOSURE]: The text references sensitive configuration files such as
auth.jsonbut only to provide guidance on maintaining authentication during isolated testing sessions. No instructions for accessing or exfiltrating these files are present.
Audit Metadata