The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill performs runtime compilation and library injection to facilitate formula recalculation.
File: scripts/office/soffice.py contains a hardcoded C source string (_SHIM_SOURCE) that is written to a temporary file and compiled using gcc via subprocess.run to create a shared library.
File: scripts/office/soffice.py uses the LD_PRELOAD environment variable to inject this compiled shim into the LibreOffice (soffice) process to modify socket behavior.
File: scripts/recalc.py dynamically generates a LibreOffice macro (Module1.xba) and writes it to the user's LibreOffice configuration directory to automate the calculateAll() and store() operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Office documents, creating a vulnerability surface if the underlying parsers are not fully hardened.
Files: scripts/office/validators/redlining.py and scripts/office/helpers/simplify_redlines.py use the standard xml.etree.ElementTree module to parse XML content from potentially untrusted .docx or .xlsx files. This module is more susceptible to certain XML-based attacks than the defusedxml library used elsewhere in the skill.
[COMMAND_EXECUTION]: The skill executes several local system tools to perform its tasks.
File: scripts/office/soffice.py executes gcc to compile the socket shim.
File: scripts/office/validators/redlining.py executes git diff via subprocess.run to generate detailed comparisons between document versions.

xlsx