present

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill generates and installs JavaScript 'document scripts' (such as main.js and config.js) from local templates into the tldraw document workspace. These scripts enable persistent behaviors like keyboard-based slide navigation and custom sidebar overlays within the application.
  • [COMMAND_EXECUTION]: The skill utilizes shell scripts (scripts/tq and scripts/new-canvas) to interact with the tldraw application's local API on localhost. These scripts manage document creation and execution of commands within the canvas environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and outlines to create slide content. This ingestion of external data into the canvas environment represents a potential attack surface, which is managed through the application's built-in sandboxing and the use of kit-standard templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 04:14 PM