excel-processor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill possesses a surface for indirect prompt injection as it processes data from external Excel files.\n
  • Ingestion points: scripts/read_excel.py and scripts/analyze_excel.py extract cell content from workbook objects.\n
  • Boundary markers: The skill returns data within structured JSON blocks, which provides a technical boundary between the data and the agent's control flow.\n
  • Capability inventory: Scripts are limited to data extraction and statistical analysis; they do not possess network or shell execution capabilities.\n
  • Sanitization: Cell values are cast to basic types (string, int, float) but are not explicitly sanitized for embedded instructions.\n- Dependency Review (SAFE): The skill relies on 'openpyxl', a well-known and trusted package for handling OpenXML files. The version constraint (>=3.1.0) avoids older versions with known XML processing vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:37 PM