The Agent Skills Directory

[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or exfiltration patterns were found. The skill correctly identifies Kubernetes Secrets as sensitive and provides best practices for managing them securely within the cluster environment.
[Remote Code Execution] (SAFE): No suspicious remote script execution patterns (such as piping curl output to bash) were detected. The use of the 'kubectl debug' command with the 'busybox:1.36' image is a standard and safe operational practice for troubleshooting.
[Privilege Escalation] (SAFE): The skill does not contain instructions to escalate local system privileges or bypass security controls. In fact, it explicitly advises against the use of 'cluster-admin' privileges and recommends following the principle of least privilege.
[Security Hardening] (SAFE): The inclusion of a dedicated security hardening reference (security-hardening.md) demonstrates a strong focus on defensive configuration, advocating for non-root execution, dropping Linux capabilities, and implementing network policies.

kubernetes