canvas-app
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution for Workspace Management: The skill utilizes shell commands (
mkdirandrm) to manage the local project directory and temporary plan files. These operations are standard for development environments to organize generated assets. - User-Input Derived Directory Naming: The skill extracts application names from user arguments and transforms them into kebab-case for use in directory creation. This transformation helps ensure that folder names are consistent and reduces the risk associated with direct shell interpolation of raw user input.
- Orchestration of Specialist Agents: The workflow delegates complex tasks (planning and screen building) to sub-agents. This modular approach is a common pattern for managing large-scale code generation tasks while maintaining clear boundaries between planning and execution.
- Validation through Compilation: The skill includes a feedback loop that uses a dedicated compilation tool to validate generated YAML files. This process ensures that errors are identified and corrected programmatically before the task is finalized.
Audit Metadata