acad-arx-wizard

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to invoke several local PowerShell scripts (e.g., New-ArxApp.ps1, New-ArxJig.ps1) to scaffold C++ projects and add-on classes. These scripts use the -ExecutionPolicy Bypass flag, which is a standard procedure for running skill-embedded scripts on Windows systems.
  • [COMMAND_EXECUTION]: Input parameters such as ProjectName and ClassName are sanitized within the scripts using regular expressions (e.g., ^[A-Za-z_][A-Za-z0-9_]*$) to ensure they are valid C++ identifiers and to prevent injection into generated source files.
  • [EXTERNAL_DOWNLOADS]: The documentation provides installation instructions via npx or git clone targeting the autodesk-platform-services/skills repository, which corresponds to the official source for these utilities.
  • [SAFE]: The skill's operations are limited to local file system activities (creating directories and writing source files based on included templates). It does not perform network requests, access sensitive user credentials, or employ any form of obfuscation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 04:51 AM
Security Audit — agent-trust-hub — acad-arx-wizard