test-windows-app

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local PowerShell scripts (scripts/uia.ps1, tools/selftest.ps1, tools/ctl.ps1) and uses the .NET CLI (dotnet test) to automate application testing and interaction.
  • [DYNAMIC_EXECUTION]: In scripts/uia.ps1, the script dynamically loads Windows UI Automation assemblies (UIAutomationClient and UIAutomationTypes) at runtime to interact with the desktop environment.
  • [PRIVILEGE_ESCALATION]: The documentation describes procedures for testing high-privilege interactions, including User Account Control (UAC) prompts and simulating global hotkeys using the PostMessage API.
  • [INDIRECT_PROMPT_INJECTION]: The UI Automation tooling reads metadata such as control names and enabled states directly from target applications, which represents an input surface for potential indirect instructions.
  • Ingestion points: scripts/uia.ps1 retrieves UI element names via the Windows.Automation.AutomationElement API.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious text embedded in UI element labels.
  • Capability inventory: The skill can execute PowerShell scripts, invoke UI patterns (buttons, selections), and send commands to a running app via named pipes.
  • Sanitization: UI element names are used and reported without sanitization or escaping mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 08:53 AM