spreadsheets

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's functionality for importing existing spreadsheet workbooks creates a surface for indirect prompt injection, where instructions embedded within spreadsheet cells could influence agent behavior.
  • Ingestion points: The SpreadsheetFile.importXlsx method, as documented in references/workbook.md, allows the loading of external file content into the workbook context.
  • Boundary markers: The skill does not provide specific delimiters or instructions to the agent to treat data within the imported spreadsheet as untrusted or separate from operational instructions.
  • Capability inventory: The skill is capable of executing JavaScript through the artifacts tool and accessing the local filesystem using node:fs/promises for file operations.
  • Sanitization: There are no specified procedures for validating or sanitizing the content of imported spreadsheets before they are processed by the agent.
  • [COMMAND_EXECUTION]: The primary function of the skill involves generating and executing dynamic JavaScript code to perform spreadsheet calculations and modifications. This execution occurs within the context of the platform's artifacts tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 12:58 PM