ai-integrations-gemini
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a legitimate integration with Gemini AI using the Google Generative AI SDK (@google/genai). It utilizes a platform-provided provisioning tool (setupReplitAIIntegrations) to securely handle API keys and base URLs without manual user intervention or exposure of secrets.
- [SAFE]: Secret management practices are sound. The skill contains explicit instructions for the AI agent to never ask the user for environment variables or modify them directly, relying instead on the automatic provisioning mechanism.
- [SAFE]: The template files provided include standard Drizzle ORM schemas and utility modules for batch processing and image generation. These use well-known, reputable packages such as 'p-limit' and 'p-retry'.
- [SAFE]: Commands executed (cp, pnpm install, codegen, db push) are standard development workflow tasks required to set up the integration and do not involve unauthorized privilege escalation or remote script execution from unknown sources.
Audit Metadata