xlsx

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The recalc.py script executes system binaries including soffice, timeout, and gtimeout using subprocess.run to perform headless Excel recalculation.
  • [COMMAND_EXECUTION]: The skill modifies the local filesystem by installing a LibreOffice Basic macro (Module1.xba) into the user's application configuration directory (~/.config/libreoffice or ~/Library/Application Support/LibreOffice) to facilitate automation.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
  • Ingestion points: The skill processes user-supplied .xlsx and .csv files via pandas and openpyxl as described in the SKILL.md and recalc.py script.
  • Boundary markers: No explicit instructions or delimiters are provided to ensure the agent ignores or sanitizes potential instructions embedded within spreadsheet cell data.
  • Capability inventory: The skill has the ability to execute shell commands and modify local files based on the processed data.
  • Sanitization: There is no evidence of validation or sanitization of data ingested from spreadsheets before it is used in calculations or workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:43 AM
Security Audit — agent-trust-hub — xlsx