xlsx

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes system binaries and dynamic code generation to facilitate its core document processing functionality.
  • The script scripts/office/soffice.py dynamically writes a hardcoded C source file and compiles it using gcc into a shared library. This library is then injected into the LibreOffice process via the LD_PRELOAD environment variable to shim socket calls, ensuring the tool works in sandboxed environments.
  • The skill executes soffice (LibreOffice) to perform headless formula recalculation and error scanning within spreadsheets.
  • It uses the git binary to perform word-level diffing between document versions to validate that changes are correctly recorded.
  • [COMMAND_EXECUTION]: The skill processes untrusted external data from spreadsheet files (.xlsx, .csv, .tsv), which constitutes an indirect prompt injection surface. The skill mitigates common risks associated with this surface by employing security-hardened XML parsing libraries such as defusedxml to prevent XML-based attacks during file processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — xlsx