The Agent Skills Directory

[SAFE]: The skill is designed for EKS cluster reconnaissance and environment discovery. It performs read-only operations to gather facts about compute, networking, security, and workloads.
[COMMAND_EXECUTION]: The skill uses aws CLI, kubectl, and helm to query cluster state. These commands are consistent with the skill's primary purpose of infrastructure discovery.
[DATA_EXPOSURE]: The skill accesses EKS and Kubernetes configuration data. This behavior is expected for a discovery tool, and no attempts to access sensitive local files (like SSH keys or credential stores) or exfiltrate data to untrusted domains were detected.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from AWS APIs and Kubernetes resources. While this represents a potential attack surface, the skill focuses on fact aggregation and lacks dangerous capabilities that could be triggered by malicious content within the cluster resources.
[FRONTMATTER]: The YAML frontmatter correctly scopes the skill's purpose and does not include any instructions to override safety guidelines or agent behavior.

eks-recon