The Agent Skills Directory

[COMMAND_EXECUTION]: The recalc.py script executes the soffice (LibreOffice) binary and system timeout utilities via subprocess.run to perform headless formula recalculation. This allows the skill to programmatically update spreadsheet values.
[DYNAMIC_EXECUTION]: The script recalc.py dynamically generates a LibreOffice Basic macro (RecalculateAndSave) and writes it to the application's configuration directory (e.g., ~/.config/libreoffice/ or ~/Library/Application Support/LibreOffice/). While this is a documented requirement for its operation, it represents the creation and storage of executable content at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various spreadsheet formats (.xlsx, .csv, .tsv), which creates an attack surface where malicious instructions embedded in data could influence agent behavior.
Ingestion points: Spreadsheet data is loaded using pandas.read_excel and openpyxl.load_workbook as described in SKILL.md.
Boundary markers: The skill does not explicitly define delimiters or instructions for the agent to treat cell content as untrusted data.
Capability inventory: The skill has the ability to execute shell commands via recalc.py and write files to the system via openpyxl.
Sanitization: There is no evidence of data sanitization or validation of the spreadsheet content before processing.

xlsx