The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell-based commands for l8k and kubectl to facilitate the deployment and verification of networking resources within a Kubernetes environment.
[CREDENTIALS_UNSAFE]: The skill references sensitive configuration files and credentials, including ~/.kube/config and Kubernetes imagePullSecrets, which are required to authenticate with clusters and private container registries. This access is consistent with the skill's stated purpose for cluster deployment and management.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect injection as it processes external configuration and manifest data.
Ingestion points: Deployment manifests located in the directory specified by --deployment-files and configuration profiles in values.yaml (SKILL.md).
Boundary markers: No specific delimiters or safety instructions are defined to separate ingested data from agent instructions.
Capability inventory: The skill executes shell commands for manifest application and interacts with the Helm SDK for chart management (SKILL.md).
Sanitization: The skill relies on the validation mechanisms inherent in the l8k and kubectl binaries.

k8s-launch-kit-deploy