The Agent Skills Directory

[SAFE]: The skill is a standard development utility for reviewing C# code. It leverages filesystem tools (Read, Glob, Grep) to analyze source files and provide feedback based on established principles like SOLID and GoF design patterns.
[INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted C# source code as its primary input. While this presents an attack surface where malicious code could contain instructions meant to influence the agent's review, the risk is minimized because the agent's capabilities are limited to read-only tools and text generation. There is no mechanism for the input code to trigger network exfiltration or unauthorized file writes.
Ingestion points: Target .cs files accessed via the Read tool.
Boundary markers: The skill does not explicitly define delimiters for the code content, relying on the model's ability to distinguish between instructions and data.
Capability inventory: Limited to Read, Glob, and Grep (read-only filesystem operations).
Sanitization: No explicit sanitization of input code is performed before analysis.

csharp-code-review