The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests repository context, including assembly metadata and configuration files, which are external data sources.
Ingestion points: The skill reads from AGENTS.md and repository assemblies to determine architectural boundaries as defined in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions defined to isolate external data from the agent's logic.
Capability inventory: The skill has the ability to modify project files, install NuGet packages, and execute shell commands (dotnet, rg) as part of its workflow.
Sanitization: The instructions do not specify any sanitization or validation routines for data retrieved from the repository.
[COMMAND_EXECUTION]: The skill utilizes standard command-line utilities to perform its tasks.
Evidence: It executes rg (ripgrep) to detect existing project configurations and dotnet for package management and running tests (SKILL.md, references/archunitnet.md).
[EXTERNAL_DOWNLOADS]: The skill automates the download of necessary libraries from official package registries.
Evidence: It installs the TngTech.ArchUnitNET core library and associated framework bridge packages (e.g., TngTech.ArchUnitNET.xUnit) via NuGet (SKILL.md).

archunitnet