xlsx
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted spreadsheet data, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: External spreadsheet files are loaded using
pd.read_excel()andload_workbook()as described inSKILL.md. - Boundary markers: The provided examples do not include delimiters or specific instructions to the agent to ignore instructions embedded within the data content.
- Capability inventory: The skill is limited to file manipulation (reading, writing, and formatting); it does not include subprocess execution, dynamic code evaluation, or network operations.
- Sanitization: There is no evidence of data validation or sanitization of the input spreadsheet contents.
Audit Metadata