agent-email-inbox

Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.

119stars16forksUpdated 5/20/2026

Data Science & ML Security Productivity & Workflow #email-processing #security #webhooks #python #javascript #automation

Security Assessment

Critical Risk(0/100)

Detected risks:

Remote Code Execution([references/webhook-setup.md] curl -fsSL https://tailscale.com/install.sh | sh)

Secret Exposure([references/webhook-setup.md] api_key =, [SKILL.md] API_KEY=, [SKILL.md] SECRET=)

Sensitive File Access([references/security-levels.md] .env, [references/webhook-setup.md] .env, [SKILL.md] .env)

Privilege Escalation([references/webhook-setup.md] sudo)

Security Score0/100

About agent-email-inbox

The `agent-email-inbox` skill enables applications and AI agents to securely receive and process inbound emails. It is designed to handle untrusted email input safely by incorporating critical security patterns such as sender allowlists, domain filtering, content validation, and sandboxed processing. By leveraging webhook-based notifications, the skill ensures that agents can respond to incoming messages in real-time without the overhead of polling for new emails, reducing both latency and API usage. This skill addresses the challenge of programmatically handling email-triggered workflows while mitigating the risks associated with untrusted sources.

FAQ

How do I set up this skill to receive emails?

You need to configure the skill with a Resend API key and optionally set a webhook secret. Emails are delivered via webhooks to your server, where the skill applies security validation before processing them.

Which programming languages are supported?

The skill works with Node.js, Python, Go, and Ruby, using the Resend SDK. Minimum SDK versions are specified in the documentation, so ensure you meet or exceed those versions.

Can I restrict which emails are processed?

Yes. You can use environment variables such as `ALLOWED_SENDERS` and `ALLOWED_DOMAINS` to limit processing to trusted senders or domains. You can also adjust the `SECURITY_LEVEL` for stricter content filtering.

What happens if an email fails security validation?

Emails that do not pass the configured security checks are rejected and not forwarded to the agent for processing, helping to prevent untrusted input from affecting your system.

Do I need to poll the inbox to receive emails?

No. The skill uses webhook-based delivery, so your server is notified immediately when an email arrives, eliminating the need for polling and reducing API calls.