The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were detected. The skill uses standard instructional language to define its operating modes.
[DATA_EXFILTRATION]: No suspicious data transfer or unauthorized access to sensitive files was found. The skill emphasizes the protection of sensitive Kubernetes objects like Secrets and etcd data for the purpose of auditing.
[REMOTE_CODE_EXECUTION]: No unauthorized remote code execution patterns were identified. The skill references reputable tools such as kubectl, helm, rbac-tool, and kube-bench for cluster analysis.
[COMMAND_EXECUTION]: The skill provides legitimate administrative commands for auditing Kubernetes clusters. It advocates for least-privilege RBAC and secure configuration of admission webhooks.
[SAFE]: All external references and dependencies target well-known and trusted organizations within the Kubernetes ecosystem, such as Argo CD, Flux, and Kyverno.

sota-kubernetes