The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard .NET CLI commands such as dotnet add, dotnet list, and common Unix utilities like head and grep for project file inspection. These are used in their intended context for software development tasks.
[PROMPT_INJECTION]: No malicious override instructions or safety bypass patterns were identified. The content uses instructional language to guide the agent in proper XML structure and project configuration.
[DATA_EXFILTRATION]: No network operations to unknown domains or attempts to access sensitive files (e.g., credentials, SSH keys) were detected. The file operations are restricted to standard .NET project files within a source code repository.
[EXTERNAL_DOWNLOADS]: References to external packages (e.g., Microsoft.EntityFrameworkCore) and documentation links target well-known and trusted sources (Microsoft Learn). No untrusted remote scripts or binaries are executed.
[INDIRECT_PROMPT_INJECTION]: While the skill involves reading and processing external data (project files), it focuses on structural XML patterns and recommends against suppressing safety analyzers (Slopwatch section), which promotes a more secure development posture.

dotnet-csproj-reading