skills/phasehq/ai/aks/Gen Agent Trust Hub

aks

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust security model for secrets, explicitly forbidding the agent from requesting, printing, or inspecting sensitive values. It provides safe, user-run commands for local execution to handle credentials like license keys and database passwords.
  • [EXTERNAL_DOWNLOADS]: Retrieves version metadata from the official Phase GitHub repository and downloads Helm charts from the vendor's repository (helm.phase.dev). These operations target trusted and well-known service providers.
  • [COMMAND_EXECUTION]: Utilizes standard, industry-standard CLI tools (az, kubectl, helm) for environment discovery and deployment. Commands are designed to run within the user's existing authenticated session with clear confirmation gates for billable resources.
  • [SAFE]: Features comprehensive preflight and capacity check modules that use read-only Azure CLI commands to verify quotas and SKU availability, ensuring infrastructure compatibility before provisioning.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 05:22 PM
Security Audit — agent-trust-hub — aks