The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading the Helm installation script directly from the official Helm project's GitHub repository.
[COMMAND_EXECUTION]: The skill permits the execution of powerful CLI tools including kubectl, helm, and kustomize, which allow for complete control over Kubernetes resources and cluster configurations.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and process data from external cluster sources that could be influenced by an attacker.
Ingestion points: Data enters the context via kubectl logs, kubectl describe, and kubectl get commands as outlined in both SKILL.md and REFERENCE.md.
Boundary markers: The skill does not define specific delimiters or instructions to treat data from logs or manifests as untrusted or separate from instructions.
Capability inventory: The skill has access to Bash (for command execution), Write/Edit (for file modification), and WebFetch (for network operations).
Sanitization: There is no mechanism described for sanitizing or validating the content of logs, events, or resource metadata before it is processed by the AI agent.

kubernetes-operations