xlsx
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill implements standard spreadsheet manipulation practices using well-known, preinstalled libraries without any malicious patterns or unsafe data exfiltration methods.
- [COMMAND_EXECUTION]: The skill utilizes shell commands to invoke LibreOffice (soffice) for the purpose of recalculating formulas in Excel workbooks and uses Python execution to perform its primary spreadsheet tasks. These operations are scoped to the intended use case of the tool.
- [SAFE]: Indirect Prompt Injection risk surface analysis: 1. Ingestion points: File reading via pandas and openpyxl as described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Python execution, shell command execution, and file write operations. 4. Sanitization: None. This risk is considered low as the surface is inherent to the core utility of processing external spreadsheet data and is subject to agent safety constraints.
Audit Metadata