ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

guava-guard

Runtime security guard for OpenClaw agents. Warns on dangerous tool call patterns. For full static scanning, use guard-scanner.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/koatora20/guava-guard
Or

GuavaGuard 🛡️

Runtime security monitoring for your OpenClaw agent.

GuavaGuard watches tool calls in real-time and warns when it detects dangerous patterns — reverse shells, credential exfiltration, sandbox escapes, and more.

Quick Start

# 1. Install
clawhub install guava-guard

# 2. Enable the runtime hook
openclaw hooks install skills/guava-guard/hooks/guava-guard
openclaw hooks enable guava-guard

# 3. Restart gateway, then verify:
openclaw hooks list   # Should show 🍈 guava-guard as ✓ ready

That's it. GuavaGuard is now monitoring your agent's tool calls.

What It Detects (12 runtime patterns)

PatternSeverityExample
Reverse shell🔴 CRITICAL/dev/tcp/, nc -e, socat TCP
Credential exfiltration🔴 CRITICALSecrets → webhook.site, ngrok, requestbin
Guardrail disabling🔴 CRITICALexec.approval = off (CVE-2026-25253)
macOS Gatekeeper bypass🔴 CRITICALxattr -d quarantine
ClawHavoc AMOS🔴 CRITICALsocifiapp, Atomic Stealer indicators
Base64 → shell🔴 CRITICALbase64 -d | bash
Download → shell🔴 CRITICALcurl | bash, wget | sh
Cloud metadata SSRF🔴 CRITICAL169.254.169.254
Known malicious IP🔴 CRITICAL91.92.242.30
DNS exfiltration🟠 HIGHnslookup $secret, dig @attacker
SSH key access🟠 HIGH.ssh/id_*, .ssh/authorized_keys
Crypto wallet access🟠 HIGHwallet seed, mnemonic, seed phrase

Current Limitation

Warning: OpenClaw's hook API does not yet support blocking tool execution. GuavaGuard currently warns only — it cannot prevent dangerous calls. When a cancel API is added, blocking will be enabled automatically. See: Issue #18677

Audit Log

All detections are logged to ~/.openclaw/guava-guard/audit.jsonl (JSON lines format).

Want Full Static Scanning? (Recommended Default)

GuavaGuard handles runtime monitoring. For comprehensive static scanning of skill packages before installation, use guard-scanner first:

# 1) Pre-install safety gate
npx guard-scanner ./skills --self-exclude --verbose

# 2) Then enable runtime monitoring
openclaw hooks enable guava-guard
  • 186+ detection patterns / 20 threat categories
  • HTML dashboard, SARIF, JSON output
  • Zero dependencies
  • MIT licensed

GitHub: https://github.com/koatora20/guard-scanner ClawHub: clawhub install guard-scanner

Born From a Real Incident

A real agent compromise overwrote core behavior files through a malicious skill install path. GuavaGuard exists to detect dangerous runtime tool-call patterns early and leave an auditable trail.

License

MIT. Zero dependencies. 🍈

Metadata

Author@koatora20
Stars1696
Views0
Updated2026-03-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-koatora20-guava-guard": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.