The Agent Skills Directory

[COMMAND_EXECUTION]: The recalc.py script executes the soffice (LibreOffice) system command via subprocess.run to perform headless formula recalculation tasks. \n- [COMMAND_EXECUTION]: The skill dynamically creates a LibreOffice Basic macro file (Module1.xba) within the user's application configuration directory to automate calculation and save operations. \n- [PROMPT_INJECTION]: The skill ingests data from external .xlsx, .csv, and .tsv files, creating a surface for indirect prompt injection where malicious instructions embedded in spreadsheet cells could attempt to influence agent behavior. \n
Ingestion points: Data is read using pd.read_excel() and load_workbook() as specified in the skill's code guidelines. \n
Capability inventory: The skill has the ability to execute shell commands and perform file system write operations. \n
Sanitization: No explicit content validation or sanitization of spreadsheet data is implemented before analysis. \n
Boundary markers: No delimiters or instructions are used to separate untrusted cell data from the agent's internal logic.

xlsx