xlsx-toolkit
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses Python's standard library for all operations, specifically zipfile and xml.etree.ElementTree. No external dependencies or remote downloads are required or performed.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted OOXML data from .xlsx files. Malicious content within sheet names, named ranges, or external link targets could potentially influence the agent's behavior during the audit process.\n
- Ingestion points: The xlsx_auditor.py script reads and parses user-supplied Excel files from the local file system.\n
- Boundary markers: The script output does not include explicit boundary markers or instructions for the agent to ignore embedded commands within the extracted data.\n
- Capability inventory: The skill is limited to file reading and XML parsing; it does not have native capabilities for network access or arbitrary command execution across its provided scripts.\n
- Sanitization: The script performs basic path sanitization for internal ZIP references but uses standard XML parsing which may be susceptible to complex XML structures in untrusted inputs.
Audit Metadata