kubernetes
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Kubernetes manifests and Helm charts, creating a potential surface for indirect prompt injection. This risk is mitigated through mandatory security verification steps, including an AI self-check checklist, server-side dry-runs, and the use of best-practice security scanners like kube-score and checkov.\n- [COMMAND_EXECUTION]: The skill utilizes administrative tools such as kubectl, helm, and argocd. It incorporates robust safety rules requiring the agent to verify the active cluster context and ensure the requester has administrative authorization before executing any commands that modify infrastructure state.\n- [EXTERNAL_DOWNLOADS]: The skill references external Helm charts and documentation. All identified sources originate from trusted organizations and well-known services, such as the official Kubernetes project and Bitnami's public OCI registry, conforming to standard and safe development practices.
Audit Metadata