airunway-aks-setup

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Command Execution via Cluster Tools: The skill utilizes kubectl and make to manage Kubernetes resources and install controllers. This is a standard operational pattern for Kubernetes-based environments, relying on the user's existing cluster permissions and context.
  • Secure Credential Handling: For gated models, the skill provides instructions to securely handle HuggingFace tokens. It uses non-echoing input methods (read -s and Read-Host -AsSecureString), stores the token in temporary files with restricted permissions (chmod 600), and ensures immediate deletion of the temporary files after creating the Kubernetes secret.
  • External Resource Interaction: The skill facilitates the download of AI models from HuggingFace, a well-known and standard service for model weights. The interaction is initiated by the user through specific model identifiers and authenticated with user-provided tokens.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — airunway-aks-setup