Take the server your AI agent runs on off the public internet: put it behind Tailscale or a Cloudflare Tunnel so only you can reach it: AI agent prompt

Lots of people now run AI agents around the clock on a rented server (a VPS). On Oct 23, 2026, as reports of hacks spread, Pieter Levels (@levelsio) reposted his advice to get any VPS off the public internet and into a Tailscale network and Cloudflare Tunnel, noting that SSH key login alone doesn't protect you from exploits and vulnerabilities; the post drew hundreds of thousands of views and thousands of bookmarks. This prompt has an AI walk you through it step by step, checking each step before you close the old door so you don't lock yourself out.

Curated by AgentPlaybook Real Estate · How we make and check prompts

SecurityAgent server lockdownintermediate

The prompt

I run an AI agent (or other apps) on a rented Linux server: [provider, e.g. Hetzner/DigitalOcean], [OS, e.g. Ubuntu 24.04]. Right now I reach it by [SSH on a public IP / a public web address]. Services on it: [list, e.g. agent dashboard on port 3000, n8n on 5678]. Help me take it off the public internet using Tailscale for my own access and, only if something must stay public, a Cloudflare Tunnel. Give me one step at a time with the exact command, what I should see if it worked, and wait for me to confirm before the next step. Order it so I can't lock myself out: install and test Tailscale access first, then close public ports in the firewall last, and tell me how to get back in through my provider's web console if something goes wrong. Finish with a short checklist to confirm nothing is still reachable from the public internet. Don't ask me for passwords or keys; tell me where to enter them myself.

Open in ChatGPT Open in Claude Perplexity Download as agent skill (SKILL.md)

How to use it

Copy the prompt above.
Replace every [bracket] with your own details (or fill in the blanks on AgentPlaybook Real Estate, which remembers your answers for the next prompt).
Paste it into Tailscale, Cloudflare Tunnel, ChatGPT and review the answer before you use it.

Works with: Tailscale, Cloudflare Tunnel, ChatGPT, Claude

Real-world example: x.com/levelsio/status/2113587042185576853

Featured in: AI prompts for writing SOPs, reports, policies and checklists

Before you use it: what to check

Already built into this prompt

Don't ask me for passwords or keys; tell me where to enter them myself.
Give me one step at a time with the exact command, what I should see if it worked, and wait for me to confirm before the next step.
Finish with a short checklist to confirm nothing is still reachable from the public internet.

Check yourself

Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.

Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.

</> Embed this prompt on your site

Paste this HTML into your blog or website. It's a plain card with no tracking scripts that links back to this prompt.

<blockquote style="border:1px solid #e4e4ee;border-left:4px solid #5b3fd9;border-radius:10px;padding:14px 16px;margin:16px 0;font-family:system-ui,sans-serif;max-width:640px"><p style="margin:0 0 6px;font-weight:700">Take the server your AI agent runs on off the public internet: put it behind Tailscale or a Cloudflare Tunnel so only you can reach it</p><p style="margin:0 0 10px;color:#5c6078;font-size:14px">Lots of people now run AI agents around the clock on a rented server (a VPS). On Oct 23, 2026, as reports of hacks spread, Pieter Levels (@levelsio) reposted his advice to get any VPS off the public internet and into a Tailscale network and Cloudflare Tunnel, noting that SSH key login alone doesn&#x27;t protect you from exploits and vulnerabilities; the post drew hundreds of thousands of views and thousands of bookmarks. This prompt has an AI walk you through it step by step, checking each step before you close the old door so you don&#x27;t lock yourself out.</p><a href="https://agentic-library.netlify.app/prompt/al-288-take-the-server-your-ai-agent-runs-on-off-the-public-interne/?utm_source=embed&amp;utm_medium=referral&amp;utm_campaign=prompt_embed" style="color:#5b3fd9;font-weight:600">Get the free AI prompt on AgentPlaybook Real Estate →</a></blockquote>

Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.

Get the free Solo Founder Stack pack

32 copy-paste agent prompts (PDF) plus 5 new prompts every week.

Get it free

More Security prompts

Draft a malware reverse-engineering briefMalware analysis · intermediate Decide which accounts your AI agent may log into and which actions still need your OK, before you hand over any passwordsAgent login permissions · beginner · worked example Run a 15-minute personal security checkup: let an AI interview you about your email, bank, phone and connected AI agents, then hand you a ranked fix listPersonal account security audit · beginner Keep the computer your AI agents run on patched every morning: one bot watches for new security advisories, another checks what's installed, applies only verified small updates and holds anything bigger for your OKPatch management · intermediate Hunt for security bugs like a team: give Claude Code a playbook built from 700+ real disclosed reports, and only test targets you're authorized to testBug bounty & testing · advanced

See all Security prompts →

Related prompts from other teams

Competitor watch reportMarketing · beginner · worked example Market size & trend reportResearch · beginner Weekly status reportOperations · beginner · worked example Write an SOP from a messy processOperations · beginner · worked example