xlsx

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes local system commands to perform spreadsheet operations. It uses the subprocess module to call the soffice binary for headless formula recalculation and employs utilities like timeout to prevent hung processes.
  • [COMMAND_EXECUTION]: The skill performs dynamic script generation by writing a LibreOffice Basic macro to the local filesystem. This macro is a static template used by the recalculation utility and does not incorporate untrusted external input into its source code.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from spreadsheet files. Ingestion points: Data is loaded via pandas.read_excel and openpyxl.load_workbook. Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands in the data. Capability inventory: The skill can write files and execute local commands through the LibreOffice interface. Sanitization: There is no evidence of sanitization or filtering of spreadsheet cell content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 01:17 AM