The Agent Skills Directory

[COMMAND_EXECUTION]: The skill heavily utilizes the dotnet CLI to perform core tasks, including running tests (dotnet test), executing test projects (dotnet run), and managing project dependencies (dotnet add). It also employs rg (ripgrep) for discovery of existing TUnit configurations within the repository.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official .NET packages, specifically the TUnit NuGet package and its associated project templates. It also provides instructions for downloading and installing necessary browser binaries for Playwright-based UI automation.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from the repository's file system, such as AGENTS.md, project files (.csproj), and test source code.
Ingestion points: Reads AGENTS.md, .csproj, Directory.Build.* files, and all .cs files in the repository to detect test configurations and code patterns.
Boundary markers: The skill does not define specific boundary markers or instructions to ignore potential commands embedded within the code or project files it analyzes.
Capability inventory: The skill possesses the capability to read/write files and execute shell commands (dotnet, rg) which could be misused if the agent is influenced by malicious content in the repository.
Sanitization: No specific sanitization or validation logic is present to filter content from input files before it influences the agent's workflow or command construction.

tunit