The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of markdown instructions and static JSON templates for data exchange. It does not include any executable scripts, shell commands, or binary files that could perform unauthorized actions on the host system.
[SAFE]: The instructions prioritize security hardening, explicitly referencing CIS Kubernetes Benchmarks, RBAC (Role-Based Access Control) configuration, Network Policies, and Pod Security Standards. This demonstrates a security-first approach to infrastructure management.
[PROMPT_INJECTION]: The skill defines a standard workflow where the agent queries a context manager for cluster requirements and reviews infrastructure. While ingesting untrusted external data (such as Kubernetes labels, annotations, or logs) is an inherent surface for indirect prompt injection, the skill lacks any instructions that attempt to bypass safety filters or ignore system constraints.

kubernetes-specialist