create-judge
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The analyzed content consists entirely of documentation and instructional steps for users to configure evaluation logic within the ZeroEval ecosystem. No executable code or suspicious patterns are present.
- [COMMAND_EXECUTION]: The skill describes how to perform API operations (POST, GET, PATCH) against a specific service to manage 'judge' configurations. These actions are aligned with the skill's stated purpose and represent standard platform interaction.
- [CREDENTIALS_UNSAFE]: The documentation includes placeholders such as
{api_key}and{project_id}for authentication and resource identification. These are standard documentation practices and do not expose sensitive information.
Audit Metadata