The Agent Skills Directory

[SAFE]: The skill performs expected scaffolding tasks using a provided Python script (scripts/create_basic_plugin.py). It includes strict normalization of user-provided plugin names to alphanumeric characters and hyphens, mitigating command injection and directory traversal risks within its scope.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface that is properly mitigated.
Ingestion points: The <plugin-name> argument and optional path parameters in the create_basic_plugin.py script.
Boundary markers: The skill generates placeholder values (e.g., [TODO: ...]) to ensure human intervention before data is used in a functional context.
Capability inventory: The skill utilizes standard library functions for directory creation and JSON file writing.
Sanitization: A strict regex-based normalization function (normalize_plugin_name) filters all non-alphanumeric characters except hyphens from user-supplied names, preventing injection attacks.

plugin-creator