메뉴
Security hardening guide for AI agents (OpenClaw/Moltbot/OpenClaw). Lock down gateway, fix permissions, set up auth. Based on real vulnerability research.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/duclm1x1/Dive-Ai --skill moltbot-openclaw-security명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | moltbot, openclaw-security |
| description | Security hardening guide for AI agents (OpenClaw/Moltbot/OpenClaw). Lock down gateway, fix permissions, set up auth. Based on real vulnerability research. |
| version | 1.0.1 |
| author | NextFrontierBuilds |
| keywords | moltbot, openclaw, openclaw, security, hardening, gateway, firewall, tailscale, ssh, authentication, ai-agent, ai-coding, claude, cursor, devops, infosec, vibe-coding |
Your Moltbot gateway was designed for local use. When exposed to the internet without proper security, attackers can access your API keys, private messages, and full system access.
Based on: Real vulnerability research that found 1,673+ exposed OpenClaw/Moltbot gateways on Shodan.
When your gateway is publicly accessible:
Prompt injection attack example: An attacker sends you an email with hidden instructions. Your AI reads it, extracts your recent emails, and forwards summaries to the attacker. No hacking required.
Run this to check your current security posture:
openclaw security audit --deep
Auto-fix issues:
openclaw security audit --deep --fix
What this does: Prevents the gateway from accepting connections from other machines.
Check your ~/.openclaw/openclaw.json:
{
"gateway": {
"bind": "loopback"
}
}
Options:
loopback — Only accessible from localhost (most secure)lan — Accessible from local network onlyauto — Binds to all interfaces (dangerous if exposed)Option A: Token Authentication (Recommended)
Generate a secure token:
openssl rand -hex 32
Add to your config:
{
"gateway": {
"auth": {
"mode": "token",
"token": "your-64-char-hex-token-here"
}
}
}
Or set via environment:
export CLAWDBOT_GATEWAY_TOKEN="your-secure-random-token-here"
Option B: Password Authentication
{
"gateway": {
"auth": {
"mode": "password"
}
}
}
Then:
export CLAWDBOT_GATEWAY_PASSWORD="your-secure-password-here"
What this does: Ensures only you can read sensitive config files.
chmod 700 ~/.openclaw
chmod 600 ~/.openclaw/openclaw.json
chmod 700 ~/.openclaw/credentials
Permission meanings:
700 = Only owner can access folder600 = Only owner can read/write fileOr let OpenClaw fix it:
openclaw security audit --fix
What this does: Stops OpenClaw from announcing itself via mDNS/Bonjour.
Add to your shell config (~/.zshrc or ~/.bashrc):
export CLAWDBOT_DISABLE_BONJOUR=1
Reload:
source ~/.zshrc
Older Node.js versions have security vulnerabilities. You need v22.12.0+.
Check version:
node --version
Mac (Homebrew):
brew update && brew upgrade node
Ubuntu/Debian:
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs
Windows: Download from nodejs.org
What this does: Creates encrypted tunnel between your devices. Access OpenClaw from anywhere without public exposure.
Install Tailscale:
# Linux
curl -fsSL https://tailscale.com/install.sh | sh
sudo tailscale up
# Mac
brew install tailscale
Configure OpenClaw for Tailscale:
{
"gateway": {
"bind": "loopback",
"tailscale": {
"mode": "serve"
}
}
}
Now access via your Tailscale network only.
For cloud servers (AWS, DigitalOcean, Hetzner, etc.)
Install UFW:
sudo apt update && sudo apt install ufw -y
Set defaults:
sudo ufw default deny incoming
sudo ufw default allow outgoing
Allow SSH (don't skip!):
sudo ufw allow ssh
Allow Tailscale (if using):
sudo ufw allow in on tailscale0
Enable:
sudo ufw enable
Verify:
sudo ufw status verbose
⚠️ Never do this:
# DON'T - exposes your gateway publicly
sudo ufw allow 18789
Disable password auth (use SSH keys):
sudo nano /etc/ssh/sshd_config
Change:
PasswordAuthentication no
PermitRootLogin no
Restart:
sudo systemctl restart sshd
Before deploying:
loopback or lan{
"gateway": {
"port": 18789,
"bind": "loopback",
"auth": {
"mode": "token",
"token": "YOUR_64_CHAR_HEX_TOKEN"
},
"tailscale": {
"mode": "serve"
}
}
}
Based on security research by @NickSpisak_ who found 1,673+ exposed gateways on Shodan.
Original article: https://x.com/nickspisak_/status/2016195582180700592
clawdhub install NextFrontierBuilds/moltbot, openclaw-security
Built by @NextXFrontier