googlesheets-automation

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint (https://rube.app/mcp). This creates a functional dependency on third-party infrastructure for tool execution.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes data from external sources.
  • Ingestion points: The agent reads untrusted content from Google Sheets using tools such as GOOGLESHEETS_BATCH_GET and GOOGLESHEETS_LOOKUP_SPREADSHEET_ROW.
  • Boundary markers: The instructions do not define delimiters or provide warnings to the agent to disregard instructions embedded within the retrieved spreadsheet data.
  • Capability inventory: The skill allows for significant operations including writing data (GOOGLESHEETS_BATCH_UPDATE), creating new spreadsheets (GOOGLESHEETS_CREATE_GOOGLE_SHEET1), and managing tool connections (RUBE_MANAGE_CONNECTIONS).
  • Sanitization: No data validation or sanitization processes are mentioned for spreadsheet content before it is used in subsequent actions.
  • [COMMAND_EXECUTION]: The skill defines workflows that execute multiple specialized tools to manage cloud-hosted spreadsheets and authentication states.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:34 PM
Security Audit — agent-trust-hub — googlesheets-automation