azure-stack-destroy

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Bash and PowerShell scripts to orchestrate the deletion of Azure Deployment Stacks and resource groups via the 'az' CLI tool. These commands are necessary for the primary function of destroying cloud deployments.
  • [SAFE]: Data ingestion occurs from a local 'state.json' file which the skill uses to identify resources for deletion. While this represents a potential surface for indirect prompt injection, the risk is mitigated by the skill's specific purpose, the requirement for user confirmation, and the use of well-defined schema fields via 'jq' and 'ConvertFrom-Json'.
  • [SAFE]: The skill performs network operations exclusively through the authenticated Azure CLI to communicate with official Microsoft Azure APIs. No unauthorized or external domains are contacted during execution.
  • [SAFE]: The scripts implement standard administrative practices, such as backgrounding long-running deletion tasks for user responsiveness and clearing subscription-scoped deployment histories to respect platform limits.
  • [SAFE]: The use of Base64 encoding in the Bash script is a standard utility pattern for processing JSON objects in a shell environment and does not constitute malicious obfuscation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 07:40 AM
Security Audit — agent-trust-hub — azure-stack-destroy