openpyxl
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documents the installation of standard packages
openpyxlandPillowfrom the Python Package Index (PyPI) and provides a reference link to a GitHub repository (github.com/theorchard/openpyxl). These actions involve well-known services and repositories and are documented neutrally. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from Excel workbooks, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: Loading existing
.xlsxor.xlsmfiles through theload_workbookfunction mentioned inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore instructions embedded within workbook data are present.
- Capability inventory: The skill utilizes the
openpyxllibrary, which provides the capability to read and write to the local file system. - Sanitization: The instructions do not include methods for sanitizing or validating data read from external files before it is processed by the agent.
Audit Metadata