winui-dev-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Indirect Prompt Injection Surface: The skill instructs the agent to read and interpret
.csprojfiles to determine target frameworks and package references. This represents an attack surface where maliciously crafted project files could attempt to influence the agent's behavior, although this is a standard requirement for development tasks. - Ingestion points: The agent reads
.csprojfiles as part of the 'Existing app' workflow (SKILL.md). - Boundary markers: None specified for the interpolation of project data.
- Capability inventory: The skill executes
dotnet add,winapp new,winapp run, andwinapp find-api(SKILL.md). - Sanitization: No explicit sanitization of project file content is described.
- Command Execution: The skill utilizes
dotnetandwinappCLI tools for project scaffolding, package management, and application execution. While these tools can perform significant system changes, the skill includes explicit instructions to respect administrative boundaries and avoid silent workarounds for tasks requiring elevated privileges.
Audit Metadata