The Agent Skills Directory

[SAFE]: The skill implements a legitimate workflow for Kubernetes resource management using official tools and following industry best practices.
[COMMAND_EXECUTION]: The skill uses kubectl to interact with Kubernetes clusters. These commands are localized to the user's intended actions (apply, delete, get status) and include appropriate validation steps.
[PROMPT_INJECTION]: The skill contains no instructions designed to override AI safety filters or hijack agent behavior. All prompts are focused on the task of generating and managing Kubernetes manifests.
[DATA_EXFILTRATION]: No evidence of hardcoded credentials, unauthorized network requests, or attempts to access sensitive local files (such as SSH keys or cloud provider configurations) was found.
[INDIRECT_PROMPT_INJECTION]: The skill processes user configuration requirements to generate YAML files. It follows secure scripting practices, such as using set -euo pipefail in shell scripts and properly quoting variables to mitigate injection risks during manifest processing.

creating-kubernetes-deployments