commandbox-developing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides comprehensive documentation for CommandBox extension development. It covers standard practices such as dependency injection via WireBox, command structure, and module configuration. All code examples use safe placeholders for sensitive information (e.g., 'your-token', 'example.com').
  • [INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting user input using the ask() and multiSelect() helpers. While these represent an input surface, the examples demonstrate benign usage (e.g., greeting the user) and provide standard guidance for CLI interactivity.
  • [COMMAND_EXECUTION]: The documentation explains how to execute shell commands using the CommandBox command() helper and shell.callCommand() method. These are documented as standard features for extension developers to integrate with the environment, rather than malicious attempts to execute arbitrary code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — commandbox-developing