cloud-architect Informe de auditoría.

Advertencias

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• SKILL.md does not explicitly define input and output artifacts for the agent, such as required inputs like current-state documentation or expected outputs like architecture diagrams and decision logs.
• No setup or prerequisites section is provided; the skill assumes AWS CLI, Azure CLI, GCP tools, and Terraform are available without explaining required local configuration or permissions.
• Limitations and safe operating boundaries are not clearly stated, such as the skill's read-only advisory nature and the need for human approval before applying infrastructure changes.
• The provided excerpt cuts off in the middle of a Terraform example; ensure the full SKILL.md is complete with all code fences properly closed.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• Dependency/runtime risk: command execution surface, credential or environment access
• Permission surface: secrets or environment access, shell or command execution

Método

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.