googlesheets-automation

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious obfuscation, persistence, or credential harvesting patterns were detected in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill directs configuration to an external MCP server at https://rube.app/mcp. This endpoint provides the necessary tools for the Google Sheets integration.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading external spreadsheet data.
  • Ingestion points: Data is ingested from Google Sheets via GOOGLESHEETS_BATCH_GET, GOOGLESHEETS_VALUES_GET, and GOOGLESHEETS_LOOKUP_SPREADSHEET_ROW as described in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or specific constraints to prevent the agent from executing instructions potentially embedded in the sheet data.
  • Capability inventory: The agent is granted powerful spreadsheet modification tools, including GOOGLESHEETS_BATCH_UPDATE, GOOGLESHEETS_UPSERT_ROWS, and GOOGLESHEETS_DELETE_DIMENSION.
  • Sanitization: No sanitization or validation procedures are established for processing the externally sourced spreadsheet data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 02:57 AM