The Agent Skills Directory

[COMMAND_EXECUTION]: The recalc.py script executes system commands including soffice (LibreOffice), timeout, and gtimeout to handle formula recalculation. These commands are executed safely using subprocess.run with arguments passed as a list, which prevents shell injection vulnerabilities.
[DYNAMIC_EXECUTION]: To enable recalculation functionality, the recalc.py script programmatically generates a LibreOffice Basic macro (Module1.xba) and installs it into the local user configuration directory (~/.config/libreoffice or ~/Library/Application Support/LibreOffice). This is a legitimate requirement for the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external spreadsheet files (.xlsx, .csv, .tsv), creating a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: External data is ingested via pandas.read_excel and openpyxl.load_workbook as described in SKILL.md.
Boundary markers: No specific delimiters or warnings for embedded instructions are defined for the processed data.
Capability inventory: The skill can write files and execute local commands (soffice) via the provided Python scripts.
Sanitization: Cell contents are processed without explicit sanitization or filtering.

xlsx