The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute dotnet build and dotnet test to verify implementation and curl to test endpoints. These are standard developer operations that run code in the local environment.
[DYNAMIC_EXECUTION]: The primary workflow of the skill involves the compilation and execution of C# source code via the .NET CLI, which constitutes a form of dynamic execution.
[INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes project files and command-line output to diagnose issues.
Ingestion points: C# source code, project configuration files, and build/test logs.
Boundary markers: The instructions do not define explicit delimiters or warnings to separate external data from instructions.
Capability inventory: The agent can execute shell commands and modify project files.
Sanitization: No data validation or sanitization steps are included for project content before processing.
[EXTERNAL_DOWNLOADS]: The skill references official Docker images from mcr.microsoft.com and redis, which are well-known and trusted service registries for development environments.
[SAFE]: The documentation link points to jeffallan.github.io, a well-known hosting service. The automated scanner alerts appear to be related to domain reputation or author context rather than malicious logic within the skill files.

dotnet-core-expert