The Agent Skills Directory

Command Execution: The skill utilizes standard command-line utilities such as kubectl and gcloud to retrieve node status, events, and configuration. These operations are diagnostic in nature and limited to read-only discovery of cluster state.
External References: It generates deep links to the Google Cloud Console Logs Explorer. These links are constructed using URL-encoded queries to provide direct access to relevant diagnostic evidence for the user. These references target a well-known service infrastructure.
Indirect Prompt Injection Surface: The skill processes output from external sources, including Kubernetes resource descriptions and system logs. While this introduces an ingestion surface for untrusted data, the skill is designed for troubleshooting where such data processing is necessary. It mitigates risk by focusing on structured evidence presentation rather than automated execution based on log content.

gke-node-notready