agent-email-inbox

Configure a secure inbound email inbox with Resend webhooks and tunneling.

159|21|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/resend/resend-skills --skill agent-email-inbox-resend
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-email-inbox
Source: https://github.com/resend/resend-skills/tree/main/agent-email-inbox
Command: npx skills add https://github.com/resend/resend-skills --skill agent-email-inbox-resend

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables AI agents to securely receive and react to inbound email, using Resend webhooks, handling tunneling for development, and enforcing strong defenses against prompt injection and other email-based attacks.

Core Features & Use Cases

  • Inbound email reception via Resend webhooks (email.received) with verified signatures.
  • Real-time notifications to your AI agent and safe routing of messages for processing.
  • Local development support with tunneling (ngrok, Cloudflare Tunnel) and guidance for secure production deployment.
  • Security-first workflow options (strict allowlists, content sanitization, sandboxed processing, and optional human-in-the-loop review).
  • Typical use cases: notifying an agent of a new customer email, triggering a contextual agent response, and validating messages before action.

Quick Start

  • Set up a receiving domain or use Resend's inbound address and verify ownership in the dashboard.
  • Create a webhook endpoint to handle email.received events and validate signatures.
  • Start a tunnel for local development (ngrok or Cloudflare Tunnel) and point the webhook to the tunnel URL.
  • Choose and configure a security level, implement content sanitization, and connect the endpoint to your AI agent.

Frequently Asked Questions about agent-email-inbox

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I receive inbound email securely using Resend webhooks for an AI agent?

Resend inbound webhooks allow your AI agent to receive email by routing email.received events to a configured endpoint, verifying webhook signatures, and safely processing the message content in real-time.

What's the best way to test inbound email webhooks during local development?

Testing inbound email webhooks locally requires setting up a development tunnel using ngrok or Cloudflare Tunnel. You point the Resend webhook endpoint to the tunnel URL to receive and validate email.received events on your local machine.

How do I prevent prompt injection attacks when an AI agent processes inbound email?

You prevent prompt injection by applying content sanitization, strict allowlists, and sandboxed processing. The skill enforces security-first workflow options to validate inbound email content before triggering any agent interactions.

Does this inbound email processing approach support human-in-the-loop review?

Yes, the skill supports optional human-in-the-loop review as part of its security levels. This allows you to validate inbound email messages and review agent interactions before executing any final actions.

Do I need a verified domain to set up secure inbound email for AI agents?

Yes, you must set up a receiving domain or use Resend's inbound address and verify ownership in the dashboard. This domain setup is required to configure the webhook endpoint for securely receiving inbound email.