create-skill
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 execute a local validation tool using
dotnet run --project eng/skill-validator/src/SkillValidator.csproj. This is a standard procedure for verifying that new skills conform to repository specifications and is intended for use within a development environment. - Indirect Prompt Injection Considerations: The skill manages the generation of metadata descriptions that influence how the agent runtime routes requests. It includes specific guidance to prevent common issues, such as avoiding XML-like tags (e.g.,
Vector<T>) that could interfere with model processing, which serves as a helpful safety and compatibility measure. - Repository Configuration: The workflow includes steps to update
.github/CODEOWNERSand directory structures. These are routine administrative tasks for maintaining project ownership and organization within a GitHub repository.
Audit Metadata