The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill contains a Python script scripts/shadcn_add.py that wraps the shadcn CLI. It uses subprocess.run with argument lists, which is a secure way to execute external commands without risking shell injection.
[EXTERNAL_DOWNLOADS] (SAFE): The documentation and scripts rely on standard package managers (npm/npx) to fetch components from trusted official registries.
[DATA_EXPOSURE] (SAFE): No evidence of sensitive data access or exfiltration was found. The skill does not interact with sensitive file paths or network endpoints other than standard package management.
[PROMPT_INJECTION] (SAFE): All markdown and code content follow the intended purpose of the skill without attempting to override agent instructions or safety protocols.

ui-styling