The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides the agent with powerful capabilities to interact with Kubernetes clusters, including kubectl apply for manifest deployment and kubectl exec for running commands directly inside containers. These are intentional and necessary for the skill's primary purpose.- [EXTERNAL_DOWNLOADS]: The skill references the Bitnami Helm repository (https://charts.bitnami.com/bitnami), which is a well-known and trusted source for container application charts.- [PROMPT_INJECTION]: There is an inherent risk of indirect prompt injection as the skill retrieves and processes untrusted data from the cluster environment.
Ingestion points: Data enters the agent context through kubectl logs, kubectl get, and helm get commands (found in SKILL.md).
Boundary markers: The instructions do not define clear boundaries or provide warnings to ignore instructions found within logs or manifests.
Capability inventory: The skill allows for significant cluster modifications via kubectl apply, kubectl exec, and helm install commands (found in SKILL.md).
Sanitization: No mechanisms are described for sanitizing or escaping the content retrieved from the cluster before the agent evaluates it.

kubernetes-helm