xlsx
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected in data processing workflows. * Ingestion points: The skill ingests data from external .xlsx, .csv, and .tsv files via pandas and openpyxl as described in the Reading and analyzing data section of SKILL.md. * Boundary markers: None; the skill lacks specific delimiters or instructions to treat spreadsheet content as untrusted data. * Capability inventory: The skill has the ability to write files (wb.save) and execute terminal commands (python recalc.py). * Sanitization: None; there is no mention of sanitizing or validating spreadsheet cell content before the agent processes it.
- [COMMAND_EXECUTION]: Local script execution for formula recalculation. * Evidence: The documentation specifies the use of a local script, recalc.py, which is invoked via python recalc.py <excel_file> to calculate values in workbooks.
- [EXTERNAL_DOWNLOADS]: Automated dependency configuration. * Evidence: The skill notes that the recalc.py script automatically configures LibreOffice on its first run, which may involve system-level package management or external downloads.
Audit Metadata