The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses subprocess.run with shlex.split to execute commands defined in ServiceConfig. In modules/execution-patterns.md, the build_command function uses .format() to inject prompts and file paths directly into command strings, which can lead to command injection if the input is not strictly validated.
[COMMAND_EXECUTION]: The ServiceConfig includes fields for auth_check_cmd and health_check_cmd, which are designed to execute arbitrary shell commands to verify service status.
[EXTERNAL_DOWNLOADS]: The skill references an external library leyline.service_registry and mentions dependencies like quota-management and usage-logging. These appear to be internal or vendor-specific modules, but they represent a dependency on external logic.

service-registry