The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/agent.py uses subprocess.run to interact with calicoctl and kubectl. These calls are used to fetch cluster state, check node health, and perform connectivity tests between pods. The commands are executed using argument lists rather than shell strings, which is a security best practice that prevents shell injection on the host system.
[DATA_EXPOSURE]: The skill collects information about Kubernetes network policies and cluster configurations to generate an audit report. This data is handled locally and output as a JSON file for the user. No evidence of external data exfiltration was found.

implementing-container-network-policies-with-calico