googlesheets-automation
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly reads and processes spreadsheet contents from user Google Sheets (e.g., GOOGLESHEETS_BATCH_GET, GOOGLESHEETS_VALUES_GET, GOOGLESHEETS_LOOKUP_SPREADSHEET_ROW) via a Google OAuth connection, which can expose arbitrary user-generated/untrusted content that the agent will read and act on.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires calling the Rube MCP endpoint (https://rube.app/mcp) at runtime via RUBE_SEARCH_TOOLS to fetch current tool schemas that directly influence the agent's available instructions and tool invocations, making it a required runtime dependency that can control agent behavior.
Audit Metadata