The Agent Skills Directory

[COMMAND_EXECUTION]: The recalc.py script executes system commands to invoke LibreOffice (soffice) and process timeouts (timeout or gtimeout on macOS) using subprocess.run.
[PERSISTENCE]: The recalc.py script modifies the local environment by creating a persistent macro file (Module1.xba) within the LibreOffice user configuration directory (e.g., ~/.config/libreoffice or ~/Library/Application Support/LibreOffice). This is used to enable the formula recalculation functionality.
[DYNAMIC_EXECUTION]: The skill uses recalc.py to programmatically generate and execute a StarBasic macro within the LibreOffice environment to perform formula evaluation.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from untrusted external spreadsheets, which creates a surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Data is read from external files using pandas.read_excel and openpyxl.load_workbook as described in SKILL.md.
Boundary markers: The instructions do not specify the use of boundary markers or instructions to ignore embedded commands when processing spreadsheet data.
Capability inventory: The skill possesses file-writing capabilities (via openpyxl) and shell execution capabilities (via recalc.py).
Sanitization: No explicit sanitization or validation logic is provided for content extracted from spreadsheet cells before it is processed by the agent.

xlsx