The Agent Skills Directory

[SAFE]: The skill's primary function is to automate a routine .NET refactoring task. It adheres to the principle of least privilege by restricting shell access to the dotnet command set.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes external source code files from the user's codebase. This is a standard risk for code-analysis tools where malicious content in the files being read could attempt to influence agent logic.
Ingestion points: Processes codebase files via Read, Glob, and Grep tools.
Boundary markers: None present in the instructions to separate untrusted code content from agent instructions.
Capability inventory: Limited to dotnet command execution and file reading/modification.
Sanitization: No sanitization or escaping of the ingested code content is described.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute dotnet build for verification purposes. The tool is appropriately restricted to the dotnet:* scope, preventing the execution of arbitrary system commands.

dotnet-source-gen-regex