---
name: agent-email-inbox
slug: agent-email-inbox
score: 61
rubric: 1.0
provenance: verified-org
publisher: Resend
license: MIT
capability: action-taking
canonical: https://top-agent-skills.com/skill/agent-email-inbox
---

# agent-email-inbox

Give an agent a webhook-driven inbox with the sender-allowlist and content-filtering patterns that block prompt injection from inbound email.

## Install

### Claude Code

```bash
npx skills add resend/resend-skills
```

### Cursor

```bash
npx skills add resend/resend-skills --target cursor
```

### Codex CLI

```bash
codex skills add resend/resend-skills/skills/agent-email-inbox
```

## Best for

Letting an agent receive and act on email safely — support triage, email-to-task pipelines, automated replies with content-safety guards.

## Not ideal for

Outbound-only sending — use the resend skill; this one is about securely processing inbound mail.

## About

Use when building any system where inbound email triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email; it carries the security patterns (sender allowlists, content filtering, sandboxed processing) that stop untrusted email from controlling your system.

## Compatibility

claude-code, cursor, codex

## Metadata

- Categories: email-messaging, security-auditing
- Tags: Inbound Email, Agent Security, Webhooks
- Setup time: 4 min
- Complexity: Medium
- Last update: 2026-04-16
- Verified: 2026-06-16
- Source: https://github.com/resend/resend-skills/tree/main/skills/agent-email-inbox


---

_Indexed by Top Agent Skills. Score breakdown: https://top-agent-skills.com/about/methodology_