The Agent Skills Directory

[SAFE]: The skill exhibits no malicious patterns. It performs document authoring and validation using standard file system operations and regex-based string manipulation consistent with the Hancom Office HWPX format.
[COMMAND_EXECUTION]: Local subprocess spawning in scripts/validate.py and various tests is used to invoke the scripts/proofread.py utility for automated quality checks. These calls are confined to local scripts and are not exploitable for arbitrary command injection.
[SAFE]: Dynamic module imports via importlib in scripts/section_transplant.py and scripts/office/pack.py are used to resolve paths for internal library components. This mechanism is restricted to the skill's own directory structure and does not involve the loading of external or untrusted code.

hwpx-core