agent-email-inbox

Name: agent-email-inbox
Author: MoizIbnYousaf

27stars5forks

How to install agent-email-inbox?

moizibnyousaf/marketing-cli/agent-email-inbox

$npx -y skills add MoizIbnYousaf/marketing-cli --skill agent-email-inbox

Installs into the current project.

Summary

Use when setting up a secure email inbox for any AI agent — configuring inbound email via Resend, webhooks, tunneling for local development, and implementing security measures to prevent prompt injection attacks. Also use when someone mentions 'agent email', 'bot inbox', 'receive

Files · 1

View on GitHub

SKILL.md

1	# AI Agent Email Inbox
2
3	Set up a secure email inbox that lets an AI agent receive and respond to emails, with protection against prompt injection and email-based attacks.
4
5	Core principle: An AI agent's inbox is a potential attack vector. Malicious actors can email instructions that the agent might blindly follow. Security configuration is not optional — it's the first thing you implement, not the last.
6
7	This skill is context-independent — it does not use `brand/` files and works identically in any project.
8
9	## On Activation
10
11	1. Ask the user which agent needs an email inbox and what framework they're using (Next.js, Express, etc.).
12	2. Determine environment: local development or production deployment.
13	3. Walk through domain setup (Resend-managed or custom).
14	4. Set up webhook endpoint with signature verification.
15	5. If local dev: configure tunneling.
16	6. Implement security level — read [references/security-levels.md](references/security-levels.md) and present options to the user.
17	7. Connect webhook to agent processing.
18
19	Output: A configured webhook handler file, environment variable checklist, and security configuration.
20
21	## Architecture
22
23	```
24	Sender → Email → Resend (MX) → Webhook → Your Server → AI Agent
25	↓
26	Security Validation
27	↓
28	Process or Reject
29	```
30
31	## Before You Start: Account & API Key Setup
32
33	Ask the user:
34	- New account just for the agent? → Simpler setup, full account access is fine
35	- Existing account with other projects? → Use domain-scoped API keys to limit what the agent can access. Even if the key leaks, it can only send from one domain.
36
37	> Don't paste API keys in chat! They'll persist in conversation history. Have the user write directly to `.env` or use a secrets manager.
38
39	## Domain Setup
40
41	### Option 1: Resend-Managed Domain (Recommended for Getting Started)
42
43	Use your auto-generated address: `<anything>@<your-id>.resend.app`. No DNS configuration needed.
44
45	### Option 2: Custom Domain
46
47	The user enables receiving in the Resend dashboard, then adds an MX record:
48
49	\| Setting \| Value \|
50	\|---------\|-------\|
51	\| Type \| MX \|
52	\| Host \| Your domain or subdomain (e.g., `agent.yourdomain.com`) \|
53	\| Value \| Provided in Resend dashboard \|
54	\| Priority \| 10 (lowest number takes precedence) \|
55
56	Use a subdomain (e.g., `agent.yourdomain.com`) to avoid disrupting existing email services on your root domain — otherwise all email routes to Resend.
57
58	## Webhook Setup
59
60	The user registers a webhook in Resend dashboard (Webhooks → Add Webhook → select `email.received`). They need the endpoint URL you'll create and the signing secret for verification.
61
62	```typescript
63	// app/api/webhooks/email/route.ts (Next.js App Router)
64	import { Resend } from 'resend';
65	import { NextRequest, NextResponse } from 'next/server';
66
67	const resend = new Resend(process.env.RESEND_API_KEY);
68
69	export async function POST(req: NextRequest) {
70	try {
71	const payload = await req.text();
72
73	const event = resend.webhooks.verify({
74	payload,
75	headers: {
76	'svix-id': req.headers.get('svix-id'),
77	'svix-timestamp': req.headers.get('svix-timestamp'),
78	'svix-signature': req.headers.get('svix-signature'),
79	},
80	secret: process.env.RESEND_WEBHOOK_SECRET,
81	});
82
83	if (event.type === 'email.received') {
84	const { data: email } = await resend.emails.receiving.get(
85	event.data.email_id
86	);
87	// Security validation happens here (see Security Levels)
88	await processEmailForAgent(event.data, email);
89	}
90
91	return new NextResponse('OK', { status: 200 });
92	} catch (error) {
93	console.error('Webhook error:', error);
94	return new NextResponse('Error', { status: 400 });
95	}
96	}
97	```
98
99	Resend retries failed deliveries with exponential backoff over ~6 hours. Emails are stored even if webhooks fail.
100
101	## Local Development with Tunneling
102
103	Your local server isn't accessible from the internet. Use tunneling to expose it:
104
105	\| Option \| Persistent URL? \| Cost \|
106	\|--------\|----------------\|------\|
107	\| ngrok (paid) \| Yes (static subdomain) \| $8/mo \|
108	\| Cloudflare named tunnel \| Yes (your own domain) \| Free \|
109	\| ngrok (free) \| No (changes on restart) \| Free \|
110	\| VS Code Port Forwarding \| No (changes per session) \| Free \|
111
112	For webhooks, persistent URLs matter — otherwise you re-register the URL every time th

People who liked this also viewed

6 picks

Type

agent-email-inbox

27stars5forks

View on GitHub

How to install agent-email-inbox?

moizibnyousaf/marketing-cli/agent-email-inbox

$npx -y skills add MoizIbnYousaf/marketing-cli --skill agent-email-inbox

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# AI Agent Email Inbox
2
3	Set up a secure email inbox that lets an AI agent receive and respond to emails, with protection against prompt injection and email-based attacks.
4
5	Core principle: An AI agent's inbox is a potential attack vector. Malicious actors can email instructions that the agent might blindly follow. Security configuration is not optional — it's the first thing you implement, not the last.
6
7	This skill is context-independent — it does not use `brand/` files and works identically in any project.
8
9	## On Activation
10
11	1. Ask the user which agent needs an email inbox and what framework they're using (Next.js, Express, etc.).
12	2. Determine environment: local development or production deployment.
13	3. Walk through domain setup (Resend-managed or custom).
14	4. Set up webhook endpoint with signature verification.
15	5. If local dev: configure tunneling.
16	6. Implement security level — read [references/security-levels.md](references/security-levels.md) and present options to the user.
17	7. Connect webhook to agent processing.
18
19	Output: A configured webhook handler file, environment variable checklist, and security configuration.
20
21	## Architecture
22
23	```
24	Sender → Email → Resend (MX) → Webhook → Your Server → AI Agent
25	↓
26	Security Validation
27	↓
28	Process or Reject
29	```
30
31	## Before You Start: Account & API Key Setup
32
33	Ask the user:
34	- New account just for the agent? → Simpler setup, full account access is fine
35	- Existing account with other projects? → Use domain-scoped API keys to limit what the agent can access. Even if the key leaks, it can only send from one domain.
36
37	> Don't paste API keys in chat! They'll persist in conversation history. Have the user write directly to `.env` or use a secrets manager.
38
39	## Domain Setup
40
41	### Option 1: Resend-Managed Domain (Recommended for Getting Started)
42
43	Use your auto-generated address: `<anything>@<your-id>.resend.app`. No DNS configuration needed.
44
45	### Option 2: Custom Domain
46
47	The user enables receiving in the Resend dashboard, then adds an MX record:
48
49	\| Setting \| Value \|
50	\|---------\|-------\|
51	\| Type \| MX \|
52	\| Host \| Your domain or subdomain (e.g., `agent.yourdomain.com`) \|
53	\| Value \| Provided in Resend dashboard \|
54	\| Priority \| 10 (lowest number takes precedence) \|
55
56	Use a subdomain (e.g., `agent.yourdomain.com`) to avoid disrupting existing email services on your root domain — otherwise all email routes to Resend.
57
58	## Webhook Setup
59
60	The user registers a webhook in Resend dashboard (Webhooks → Add Webhook → select `email.received`). They need the endpoint URL you'll create and the signing secret for verification.
61
62	```typescript
63	// app/api/webhooks/email/route.ts (Next.js App Router)
64	import { Resend } from 'resend';
65	import { NextRequest, NextResponse } from 'next/server';
66
67	const resend = new Resend(process.env.RESEND_API_KEY);
68
69	export async function POST(req: NextRequest) {
70	try {
71	const payload = await req.text();
72
73	const event = resend.webhooks.verify({
74	payload,
75	headers: {
76	'svix-id': req.headers.get('svix-id'),
77	'svix-timestamp': req.headers.get('svix-timestamp'),
78	'svix-signature': req.headers.get('svix-signature'),
79	},
80	secret: process.env.RESEND_WEBHOOK_SECRET,
81	});
82
83	if (event.type === 'email.received') {
84	const { data: email } = await resend.emails.receiving.get(
85	event.data.email_id
86	);
87	// Security validation happens here (see Security Levels)
88	await processEmailForAgent(event.data, email);
89	}
90
91	return new NextResponse('OK', { status: 200 });
92	} catch (error) {
93	console.error('Webhook error:', error);
94	return new NextResponse('Error', { status: 400 });
95	}
96	}
97	```
98
99	Resend retries failed deliveries with exponential backoff over ~6 hours. Emails are stored even if webhooks fail.
100
101	## Local Development with Tunneling
102
103	Your local server isn't accessible from the internet. Use tunneling to expose it:
104
105	\| Option \| Persistent URL? \| Cost \|
106	\|--------\|----------------\|------\|
107	\| ngrok (paid) \| Yes (static subdomain) \| $8/mo \|
108	\| Cloudflare named tunnel \| Yes (your own domain) \| Free \|
109	\| ngrok (free) \| No (changes on restart) \| Free \|
110	\| VS Code Port Forwarding \| No (changes per session) \| Free \|
111
112	For webhooks, persistent URLs matter — otherwise you re-register the URL every time th

People who liked this also viewed

6 picks

Type