winui-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill instructs the agent to use a command-line utility (
winapp) to verify API availability and compatibility within the specific project directory. This is a functional requirement for providing accurate code review feedback based on the project's actual dependencies and environment. - Indirect Prompt Injection Surface: The skill is designed to ingest and analyze untrusted source code (XAML and C# files) to identify quality issues. This represents a potential indirect prompt injection surface where adversarial content could be embedded in code comments or string literals. However, this is inherent to the skill's purpose as a code analyzer, and the risk is managed through standard platform-level safety guardrails.
- Security Best Practices: The documentation explicitly guides users to avoid common security vulnerabilities, such as hardcoding credentials or using unsanitized input in process execution. These instructions serve to improve the security of the target application rather than introducing risks to the agent's environment.
- Vendor-Owned Tooling: The skill references specific Microsoft-centric development tools and patterns (e.g., WinAppSDK, WinUI 3, and specialized analyzers) which are consistent with its stated purpose of assisting in Windows application development.
Audit Metadata