xlsx
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external spreadsheet files (.xlsx, .csv, etc.), which creates a potential surface for indirect prompt injection attacks if the data contains hidden instructions.
- Ingestion points: Spreadsheet data is loaded into the environment using
pd.read_excel()as documented inSKILL.md. - Boundary markers: The instructions do not define delimiters or warnings to prevent the agent from executing instructions found within the data.
- Capability inventory: The skill possesses file read and write capabilities using the
pandaslibrary. - Sanitization: There is no requirement or implementation shown for sanitizing or escaping content retrieved from the spreadsheets.
Audit Metadata