azure-local-multi-rack

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • Standard Tooling and Extensions: The skill utilizes official Azure CLI extensions (networkcloud, managednetworkfabric, stack-hci-vm). These represent standard vendor-provided management tools from Microsoft and are used according to established practices.
  • Safety-First Design: The skill includes a dedicated 'Safety Rules' reference and multiple workflow guardrails. These prioritize read-only operations first and mandate explicit user consent before executing any modifications, power operations, or fabric changes, which significantly reduces the risk of accidental or unauthorized impact.
  • Trusted Documentation: All external references point to the official Microsoft Learn domain (learn.microsoft.com). This ensures that the agent and user rely on authoritative, vendor-verified guidance for complex infrastructure tasks.
  • Information Ingestion Surface: As a management skill, it naturally processes user-supplied resource identifiers (IDs, names) to generate commands. While this creates a surface for indirect prompt injection, the skill mitigates this by instructing the agent to validate state and obtain confirmation before acting on generated commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-local-multi-rack