vm-lifecycle-manager

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a mandatory 'Human-in-the-Loop' protocol, requiring explicit user confirmation before executing any tool commands that change the power state of a virtual machine.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The instructions contain clear security warnings to never display the KUBECONFIG path or credential values to the user, protecting sensitive cluster access information.
  • [EXTERNAL_DOWNLOADS]: The skill references an MCP server from the 'openshift' GitHub organization (openshift/openshift-mcp-server). As this is a well-known organization, the reference is considered safe and standard for the skill's operational context.
  • [COMMAND_EXECUTION]: While the skill executes commands via the vm_lifecycle tool, these are limited to predefined actions (start, stop, restart) on specific Kubernetes resources, and the workflow requires verification steps to ensure state consistency.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 04:04 PM