office-excel

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the uv tool to execute Python scripts, which involves downloading the openpyxl package from the official Python Package Index (PyPI).
  • [PROMPT_INJECTION]: The skill handles data from external sources including Excel spreadsheets, Markdown files, and JSON data, which constitutes an indirect prompt injection surface.
  • Ingestion points: The scripts read_excel.py and write_excel.py ingest data from user-provided file paths and standard input.
  • Boundary markers: There are no specific delimiters or instructions provided to the agent to differentiate between data content and potential embedded instructions.
  • Capability inventory: The skill allows for local file system read and write operations.
  • Sanitization: The content is parsed into structured formats but is not filtered for instruction-like strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 02:29 PM
Security Audit — agent-trust-hub — office-excel