The Agent Skills Directory

[COMMAND_EXECUTION]: The skill defines various kubectl commands for managing AKS and ARO clusters. These include retrieving node and pod status, viewing logs, describing resources, and executing commands within pods. These are standard administrative operations intended for DevOps and SRE workflows.- [PROMPT_INJECTION]: The skill processes external data via Kubernetes manifests and cluster outputs, which constitutes an indirect prompt injection surface.
Ingestion points: The skill ingests user-provided manifest.yaml files and retrieves data from the cluster API via kubectl logs, kubectl get, and kubectl describe.
Boundary markers: No explicit boundary markers or 'ignore' instructions are provided for processed data.
Capability inventory: Includes the ability to create, modify, and delete cluster resources, as well as execute arbitrary commands within pod containers via kubectl exec.
Sanitization: No sanitization logic is present; the skill relies on the agent's default handling of CLI outputs and manifest contents.

kubectl-cli