skills/answerzhao/agent-skills/xlsx/Gen Agent Trust Hub

xlsx

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes the soffice binary (LibreOffice) to perform formula recalculation in headless mode. The script uses list-based arguments with subprocess.run, which is a secure practice that prevents shell command injection vulnerabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external spreadsheet files, which is a potential surface for indirect prompt injection. Ingestion points: The skill ingests data from external files using pandas.read_excel and openpyxl.load_workbook. Boundary markers: The instructions do not define specific delimiters or isolation protocols for external data. Capability inventory: The skill possesses file system write capabilities and the ability to execute the recalc.py script. Sanitization: No explicit sanitization or validation of spreadsheet cell content is performed before processing by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:41 PM