xlsx

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local Python script, scripts/recalc.py, to perform Excel formula recalculation via LibreOffice. This is an intended functional requirement for updating values in files modified with openpyxl and does not represent a security risk within the skill's context.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process external spreadsheet data, which is an inherent surface for indirect prompt injection.
  • Ingestion points: Data is loaded from user-provided files using pandas.read_excel and openpyxl.load_workbook as specified in SKILL.md.
  • Boundary markers: No specific delimiters or instructions to ignore embedded instructions in cell content are provided.
  • Capability inventory: The skill can write to the local file system and execute the scripts/recalc.py script.
  • Sanitization: No input validation or sanitization logic for cell data is described. While the surface exists, the instructions focus on technical data manipulation rather than unrestricted interpretation of cell content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:22 PM
Security Audit — agent-trust-hub — xlsx