xlsx

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes the LibreOffice (soffice) utility via subprocess.run to recalculate spreadsheet formulas. This is a primary function of the skill and uses list-based arguments for safe execution.
  • [COMMAND_EXECUTION]: The recalc.py script programmatically creates a LibreOffice Basic macro within the user's application configuration directory to automate calculation and saving. This configuration is necessary for the skill's headless operation and is limited to the current user's environment.
  • [PROMPT_INJECTION]: The skill ingests data from untrusted Excel spreadsheets, creating a surface for indirect prompt injection.
  • Ingestion points: Spreadsheets read via pandas or openpyxl as described in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: File system access and shell command execution through the provided Python tools.
  • Sanitization: No input validation or sanitization is specified for external spreadsheet content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 01:37 AM
Security Audit — agent-trust-hub — xlsx