06-k8s-triage
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a strictly read-only workflow for Kubernetes cluster investigation, including explicit prohibitions against commands that modify cluster state such as
apply,delete,patch, orscale. - [SAFE]: Data protection measures are integrated into the instructions, specifically directing the agent to avoid printing the values of sensitive environment variables like secrets, tokens, and passwords during pod diagnostics.
- [SAFE]: No remote code execution or external network operations were detected. All triage actions are performed locally using standard command-line tools.
- [SAFE]: The skill uses a discovery-driven workflow where target resource names are retrieved directly from the cluster prior to inspection, reducing the risk of processing malicious inputs.
Audit Metadata