The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local Python script (scripts/docx_tool.py) to generate or edit Word documents. This is a standard use of a programmatic helper within the skill's intended purpose.
[DATA_EXPOSURE]: The extract command in the provided script reads the content of .docx files. This is limited to files specified by the user or generated by the skill and does not target sensitive system locations.
[REMOTE_CODE_EXECUTION]: The skill uses a 'zero-dependency' script that relies solely on the Python standard library (zipfile, xml.sax.saxutils, etc.). It does not download external packages or execute code from remote URLs.
[PROMPT_INJECTION]: No malicious patterns or attempts to override agent safety guidelines were detected in the instructions. The quality checks and anti-patterns focus on document formatting and integrity.

word-document