cloud-management

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements robust security guardrails, including a mandatory approval model described in 'references/approval-policy.md' and a specialized risk-scoring script 'scripts/cloud_change_guard.py' that must be run before any destructive, expensive, or security-sensitive operation.
  • [COMMAND_EXECUTION]: The skill utilizes local Python helper scripts to automate tasks such as repository analysis and infrastructure scaffolding. The 'scripts/terraform_scaffolder.py' script executes the 'terraform' or 'tofu' binary locally to validate generated modules. These executions use hardcoded arguments and are consistent with the skill's stated purpose of managing infrastructure.
  • [DATA_EXPOSURE]: The skill is designed to interact with cloud environments but emphasizes secure credential management. It explicitly instructs the assistant to favor short-lived credentials, SSO, and OIDC federation over static keys, and to use provider-native secret stores (AWS Secrets Manager, Azure Key Vault, GCP Secret Manager).
  • [EXTERNAL_DOWNLOADS]: All external references and command examples target official and well-known cloud provider domains (e.g., amazonaws.com, azure.com, google.com) or the author's official GitHub repository, which is consistent with the skill's utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 08:09 PM
Security Audit — agent-trust-hub — cloud-management