acad-arx-wizard
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the AI agent to run local PowerShell scripts (New-ArxApp.ps1, etc.) using the -ExecutionPolicy Bypass flag. This is a standard method for ensuring scaffolding scripts can run regardless of the local system's PowerShell restriction level.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user input for project names and class names which are then inserted into code templates. The skill includes basic sanitization (New-SafeName) to ensure these inputs conform to C++ identifier rules, effectively managing the risks associated with data interpolation in generated code.
Audit Metadata