chatgpt-app-builder
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform standard development tasks using the shell, such as scaffolding new projects (
npm create skybridge), installing dependencies (npm install,pnpm install, etc.), and starting development servers. These commands are necessary for the skill's functionality and are appropriately scoped to the user's project directory. - [EXTERNAL_DOWNLOADS]: The skill downloads project templates and framework components from the official NPM registry and GitHub repositories associated with the Alpic and Skybridge organizations. These are trusted sources for the intended development workflow.
- [REMOTE_CODE_EXECUTION]: The skill utilizes
npxto execute platform-specific CLI tools (e.g.,alpic,chrome-devtools-mcp) directly from the NPM registry. This is a standard practice for ensuring the latest versions of developer tools are used during deployment and local testing. - [SAFE]: All identified capabilities, including network operations for local tunnels (
alpic tunnel) and shell commands for deployment, are consistent with the skill's documented purpose as a developer guide for the Skybridge framework. The external resources used are either official vendor infrastructure or well-known service providers (OpenAI, Anthropic, Stripe, Auth0, etc.).
Audit Metadata