xlsx

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The recalc.py script dynamically generates a StarBasic macro and writes it to the user's local LibreOffice configuration directory (e.g., ~/.config/libreoffice/...). This macro is then executed via the soffice command-line interface to perform formula recalculations that are not supported by the Python openpyxl library alone.
  • [COMMAND_EXECUTION]: The recalc.py script uses subprocess.run to execute the soffice (LibreOffice) binary and system utilities like timeout or gtimeout. These commands are used to automate the opening, recalculating, and saving of Excel workbooks.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process data from external Excel files, which represents a surface for indirect prompt injection. Malicious data or formulas within a spreadsheet could potentially influence the agent's reasoning or actions.
  • Ingestion points: Data is loaded from .xlsx, .xlsm, .csv, and .tsv files using pandas and openpyxl as described in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore" instructions are provided to the agent for handling content read from spreadsheet cells.
  • Capability inventory: The skill possesses file system access, shell command execution (via recalc.py), and the ability to generate documentation containing URLs.
  • Sanitization: There is no evidence of sanitization or validation logic for external data processed by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:11 PM
Security Audit — agent-trust-hub — xlsx