building-edgespark-apps
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill includes explicit instructions to ensure that sensitive data, such as secrets and API keys, are never handled directly by the AI agent or passed through the CLI. It directs the agent to provide a secure URL to the user for browser-based entry, ensuring credentials do not enter the agent's context or conversation history.
- [COMMAND_EXECUTION]: The skill enables the agent to perform development tasks by executing the
edgesparkCLI. This includes commands for project initialization, database migrations, and application deployment, which are standard and expected functions for this vendor's development toolset. - [EXTERNAL_DOWNLOADS]: The skill references and utilizes the
@edgespark/webNode.js package and other standard libraries likehonoanddrizzle-ormfor application development. These resources are standard for the platform's intended full-stack and server-side workflows.
Audit Metadata