build-and-verify

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local PowerShell scripts such as ./build.ps1, tools/snap.ps1, tools/grid-lint.ps1, tools/check-layout.ps1, and tools/selftest.ps1, along with CLI tools like dotnet and msbuild to automate the build and verification process of Windows applications.\n- [DYNAMIC_EXECUTION]: The skill facilitates the compilation and execution of WinUI 3, WPF, and WinForms applications using standard .NET development toolchains. These operations are restricted to the local development environment for the purpose of UI verification.\n- [INDIRECT_PROMPT_INJECTION]: The skill involves processing external data which creates a potential injection surface. 1. Ingestion points: Application logs (APP_LOG), source code (XAML, C#), and generated snapshot metadata. 2. Boundary markers: No explicit delimiters or warnings are defined for these inputs. 3. Capability inventory: Local shell execution for build and test scripts, and file reading via the Read tool. 4. Sanitization: No explicit sanitization of log content or metadata is described before agent processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 08:53 AM