choose-metric
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses specific Harness MCP and CLI tools (
harness_get,harness_list,harness get,harness list) to interact with flags, experiments, and metrics. These are recognized as legitimate vendor resources and are used for their intended purpose within the platform. - [SAFE]: The instructions emphasize establishing organizational and project scope before performing any operations (Phase 1), which is a security best practice for managing data access.
- [SAFE]: The skill performs read-only operations to inventory and health-check existing metrics. It explicitly delegates modification tasks, such as creating or instrumenting metrics, to other specialized skills, adhering to the principle of least privilege.
- [SAFE]: No obfuscation, prompt injection, or unauthorized network operations were identified. All internal references point to local documentation within the repository structure.
Audit Metadata