generate-canvas-app

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Local Command Execution: The skill utilizes Bash to create a dedicated working directory and perform cleanup of temporary plan files. These operations are scoped to the project folder derived from the user's requirements.
  • Agent Orchestration and Task Management: This skill orchestrates the creation of specialized sub-tasks (canvas-app-planner and canvas-screen-builder) to modularize the application generation process. The usage of the Task tool is confined to internal agent coordination.
  • Input Interpolation in Multi-Agent Workflows: User-provided requirements are interpolated into prompts for secondary agents. This establishes a surface where the content of the user's request influences the behavior of the planning and building agents, which is central to the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 06:02 PM