The Agent Skills Directory

[COMMAND_EXECUTION]: The recalc.py script executes system commands including soffice (LibreOffice) and timeout/gtimeout utilities via the subprocess.run method.
[COMMAND_EXECUTION]: The recalc.py script performs dynamic script generation by writing a hardcoded LibreOffice Basic macro (Module1.xba) to the user's local configuration directory (~/.config/libreoffice or ~/Library/Application Support/LibreOffice) and subsequently executing it.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external Excel and CSV files through its instructions.
Ingestion points: Spreadsheet data is loaded into the agent's context via pd.read_excel() and load_workbook() calls as described in SKILL.md.
Boundary markers: Absent; the instructions do not specify any delimiters or warnings to ignore instructions that might be embedded within the processed data.
Capability inventory: The skill possesses file system write access and the ability to execute shell commands via the recalc.py script.
Sanitization: There is no provided logic or instruction to sanitize, validate, or escape the content of the spreadsheets before they are processed by the agent.

xlsx