The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the repository environment which could influence agent behavior through indirect prompt injection.
Ingestion points: The skill reads configuration and command overrides from AGENTS.md and evaluates project structure from .csproj files as part of its workflow.
Boundary markers: There are no explicit delimiters or instructions to the agent to distinguish between its own system instructions and potentially malicious instructions embedded in the project files it reads.
Capability inventory: The skill leverages powerful CLI capabilities including dotnet test, dotnet run, and dotnet add package to modify the project environment or execute code.
Sanitization: No explicit sanitization or validation of the commands retrieved from AGENTS.md is specified before they are passed to the shell for execution.
[COMMAND_EXECUTION]: Interacts with the local system via shell commands to facilitate test execution and project management as part of its primary functionality.
Evidence: Employs dotnet test, dotnet run, and rg (ripgrep) for discovering and executing tests within the local environment.
[EXTERNAL_DOWNLOADS]: Fetches and installs external dependencies from public package registries to configure the testing environment.
Evidence: Utilizes dotnet add package to install official xunit.v3 and related testing packages from the NuGet registry.

dotnet-xunit