The Agent Skills Directory

[COMMAND_EXECUTION]: The skill workflow involves executing several shell commands to manage the development lifecycle, including mkdir for directory creation, and dotnet build and dotnet run for compiling and executing the generated module code.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted user requirements to generate code files (Category 8). There is a risk that an attacker could provide requirements that include malicious code, which would then be written to the local filesystem and executed during the build process.
Ingestion points: User-provided descriptions of module functionality, content parts, and fields (processed in SKILL.md and applied to templates in the references directory).
Boundary markers: Absent. The skill does not implement specific delimiters or 'ignore' instructions to separate user input from the code generation logic.
Capability inventory: The skill possesses the ability to create directories, write files, and execute build/run commands via the .NET SDK on the host system.
Sanitization: Absent. There is no evidence of validation, escaping, or filtering of user input before it is interpolated into C# templates or Razor views.

orchardcore-module-creator