xlsx
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The recalc.py script executes system commands using subprocess.run to invoke LibreOffice (soffice) and system timeout utilities (timeout or gtimeout) for spreadsheet processing.
- [COMMAND_EXECUTION]: The script dynamically generates a LibreOffice Basic macro file (Module1.xba) and writes it to the user's configuration directory (~/.config/libreoffice or ~/Library/Application Support/LibreOffice) to enable automated formula recalculation.
- [PROMPT_INJECTION]: The skill processes external data files, which presents a surface for indirect prompt injection attacks. * Ingestion points: Excel, CSV, and TSV files are read into the agent context using pandas.read_excel and openpyxl.load_workbook as instructed in SKILL.md. * Boundary markers: The skill does not implement delimiters or instructions to isolate external data from the agent's command logic. * Capability inventory: The skill has the capability to execute system commands and perform filesystem writes via the recalc.py script. * Sanitization: No data validation or content filtering is applied to the spreadsheet content before it is processed by the agent.
Audit Metadata