The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes C# source files and project configurations which could contain malicious instructions designed to subvert the agent's behavior.
Ingestion points: Processes .cs and .csproj files using Read, Glob, and Grep (SKILL.md).
Boundary markers: Absent. The skill does not use specific markers to distinguish code from instructions.
Capability inventory: The skill employs Edit and Write tools to modify local files and suggests the use of the dotnet test command (SKILL.md).
Sanitization: Absent. There is no logic to filter or sanitize the contents of the files before analysis.
[COMMAND_EXECUTION]: The skill guidelines specify the execution of dotnet test to verify code changes. While this is a standard development practice, it allows the agent to execute project-defined code.

csharp-refactor