google-sheets-automation

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands to execute Python scripts (scripts/auth.py and scripts/sheets.py) for managing OAuth authentication and performing spreadsheet operations like reading, updating, and appending data.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates network communication with Google's APIs to retrieve and send spreadsheet data. It also references an automated token refresh mechanism involving a cloud function, which is standard for long-term OAuth access.
  • [PROMPT_INJECTION]: The skill processes data from external spreadsheets (Indirect Prompt Injection surface).
  • Ingestion points: Untrusted data enters the agent context via scripts/sheets.py get-text and get-range commands.
  • Boundary markers: None explicitly defined in the provided instructions to separate spreadsheet content from system prompts.
  • Capability inventory: The skill has write capabilities including update-range, append-rows, and batch-update across all scripts.
  • Sanitization: No specific sanitization or validation of the retrieved spreadsheet content is mentioned before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:34 PM
Security Audit — agent-trust-hub — google-sheets-automation