Skills
Navigate
skills/managedcode/dotnet-skills/winforms-expert/Gen Agent Trust Hub

winforms-expert

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands to validate UI changes and build projects. Evidence: Instructions in SKILL.md to run pwsh -NoProfile -File <task-validator.ps1> <scenario-arguments> and dotnet build <project> --nologo.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from the workspace, including source code and configuration files, creating a potential surface for indirect prompt injection from malicious project files. Ingestion points: WinForms project files, designer files (*.Designer.cs/*.Designer.vb), and .resx resources. Boundary markers: The skill does not provide specific instructions to the agent to ignore embedded instructions within processed data. Capability inventory: Execution of local PowerShell scripts and .NET build commands. Sanitization: No explicit input sanitization or script argument validation is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 05:11 AM