The Agent Skills Directory

[Indirect Prompt Injection Surface]: The skill is designed to interact with live cluster data and apply configuration changes, creating a surface where data retrieved from the cluster could potentially influence the agent's subsequent actions.
Ingestion points: Data is retrieved from the cluster environment using tools such as get_cluster and get_k8s_resource (SKILL.md).
Boundary markers: The instructions focus on structured configuration values and defaults, but do not explicitly define delimiters for separating untrusted cluster data from the agent's instructions.
Capability inventory: The skill has the capability to modify the environment through tools like update_cluster and apply_k8s_manifest (SKILL.md).
Sanitization: The skill relies on standard platform-level validation for GKE configurations and does not implement additional local filtering of retrieved data.

gke-networking