xlsx
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script,
scripts/recalc.py, to recalculate Excel formulas using an installed LibreOffice instance. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from spreadsheet files (XLSX, XLSM, CSV, TSV) and possesses file-writing and local command execution capabilities.
- Ingestion points: External tabular files loaded into the agent's context using
pd.read_excel()oropenpyxl.load_workbook(). - Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions embedded within the spreadsheet data.
- Capability inventory: The skill can perform file system writes (
wb.save,df.to_excel) and execute the localscripts/recalc.pyscript. - Sanitization: No data validation or sanitization procedures are mentioned for the content being read from external files.
Audit Metadata