skills-eval
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a set of local analysis tools for evaluating the structural integrity and performance of other agent skills, which is a legitimate development workflow.
- [SAFE]: The deployment script (
deploy.sh) automates the setup process by making included scripts executable, which is standard behavior for the installation of CLI utilities. - [SAFE]: The documentation includes educational content on prompt engineering and pressure testing; these sections provide templates and examples for testing skill resilience and do not attempt to manipulate the current agent's safety protocols.
- [SAFE]: No evidence of data exfiltration, credential harvesting, or unauthorized network operations was found. The skill focuses on local metrics and adherence to Claude Agent SDK standards.
Audit Metadata