openclaw-shield
Security audit engine for OpenClaw configurations. Detects vulnerabilities, misconfigurations, secret leaks, and over-privileged agents. Use when the user asks about security, hardening, config review, or audit of their OpenClaw setup.
Install
npx skills add https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/ai-shield-audit
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install aaaaqwq-agi-super-team@llmmart
git clone https://github.com/aAAaqwq/AGI-Super-Team.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole aaaaqwq/agi-super-team collection as a plugin from our marketplace. Git is the plain clone.
README
🛡️ OpenClaw Shield
Security audit engine for OpenClaw configurations. Find vulnerabilities, misconfigurations, and secret leaks before they become breaches.
Built by Autonomous Intelligence — we run 9 agents in production. We know what breaks.
Features
- 11 security check categories covering auth, networking, channels, agents, secrets, and more
- Structured JSON reports with risk scores, severity levels, and remediation steps
- Config sanitizer to strip secrets before sharing
- CLI tool for quick audits
- Zero dependencies — pure Node.js, no npm install needed
Quick Start
# Audit your live config
node bin/shield.js audit ~/.openclaw/openclaw.json --summary
# Get JSON report
node bin/shield.js audit ~/.openclaw/openclaw.json
# Strip secrets before sharing
node bin/shield.js sanitize ~/.openclaw/openclaw.json > safe-config.json
Sample Output
╔══════════════════════════════════════════════════╗
║ 🛡️ OpenClaw Shield Audit Report ║
╚══════════════════════════════════════════════════╝
Risk Level: HIGH
Score: 42/100
Safe to Deploy: ❌ No
Action: REVIEW_AND_REMEDIATE
Vulnerabilities: 12
🔴 Critical: 2
🟠 High: 3
🟡 Medium: 4
🔵 Low: 3
Security Checks
| # | Category | What It Catches |
|---|---|---|
| 1 | Gateway Auth | Missing auth token, insecure UI, weak tokens |
| 2 | Network Exposure | Non-loopback bind, Tailscale funnel, wildcard proxies |
| 3 | Channel Security | Wildcard allowFrom, missing allowlists |
| 4 | DM Policy | Open DM policy without pairing |
| 5 | Subagent Permissions | Wildcard allowAgents, circular chains, self-spawn |
| 6 | Tool Permissions | Over-privileged agents (full tool access) |
| 7 | Secret Leakage | API keys, tokens, private keys in plaintext |
| 8 | Sandbox/Execution | Missing workspace isolation, no exec policies |
| 9 | Plugin Config | Orphaned plugins, missing channel configs |
| 10 | Heartbeat Exposure | Sensitive data in heartbeat prompts |
| 11 | Remote Config | Unencrypted WebSocket, exposed remote tokens |
JSON Report Schema
{
"risk_level": "CRITICAL|HIGH|MEDIUM|LOW",
"overall_score": 0-100,
"vulnerabilities": [{
"category": "string",
"severity": "critical|high|medium|low",
"issue": "Description of the problem",
"recommendation": "How to fix it",
"auto_fix": { "path": "config.path", "value": "suggested_value" }
}],
"vulnerability_count": { "critical": 0, "high": 0, "medium": 0, "low": 0, "total": 0 },
"best_practices_compliance": 0.0-1.0,
"action_recommended": "BLOCK|REVIEW_AND_REMEDIATE|APPROVE",
"safe_to_deploy": true|false,
"audit_timestamp": "ISO8601",
"engine_version": "1.0.0"
}
Programmatic Usage
const { auditConfig } = require('./src/audit');
const { sanitizeConfig } = require('./src/sanitize');
// Audit
const config = require('./my-openclaw.json');
const report = auditConfig(config);
if (!report.safe_to_deploy) {
console.log(`${report.vulnerability_count.critical} critical issues found!`);
}
// Sanitize before sharing
const clean = sanitizeConfig(config);
Pricing
- Local audit: Free (install the skill, run locally)
- Premium remote audit: $0.10/audit via ACP (deeper analysis + auto-fix patches)
License
MIT — Autonomous Intelligence 2026
Skill manifest
OpenClaw Shield — Security Audit
Audit any OpenClaw config for security vulnerabilities, misconfigurations, and best-practice violations. Produces a structured JSON report with risk scores, findings, and remediation steps.
When to Use
- User asks to check/audit/review their OpenClaw security
- User wants to harden their config before deploying
- User is setting up a new OpenClaw instance
- User asks about secret leakage or API key exposure in their config
- Before publishing or sharing any config file
Quick Audit (live config)
node scripts/shield-audit.sh
Or directly:
node SKILL_DIR/bin/shield.js audit ~/.openclaw/openclaw.json --summary
What It Checks (11 categories)
- Gateway Auth — missing/weak auth, insecure UI settings
- Network Exposure — bind address, Tailscale funnel, wildcard proxies
- Channel Security — wildcard allowFrom, missing allowlists
- DM Policy — open DM policy without pairing
- Subagent Permissions — wildcard allowAgents, circular delegation chains, self-delegation
- Tool Permissions — over-privileged agents with tools.profile: "full"
- Secret Leakage — API keys, tokens, private keys in plaintext config
- Sandbox/Execution — missing workspace isolation, no execution policies
- Plugin Config — enabled plugins without channel config
- Heartbeat Exposure — sensitive data in heartbeat prompts
- Remote Config — unencrypted WebSocket, exposed remote URLs/tokens
Usage
Audit a config file
node SKILL_DIR/bin/shield.js audit <config.json>
node SKILL_DIR/bin/shield.js audit <config.json> --summary # human-readable
Audit from stdin
cat config.json | node SKILL_DIR/bin/shield.js audit --stdin
Sanitize a config (strip secrets)
node SKILL_DIR/bin/shield.js sanitize <config.json>
Programmatic use
const { auditConfig } = require('SKILL_DIR/src/audit');
const config = require('./openclaw.json');
const report = auditConfig(config);
console.log(report.risk_level); // "CRITICAL" | "HIGH" | "MEDIUM" | "LOW"
console.log(report.overall_score); // 0-100
console.log(report.vulnerabilities); // detailed findings
Output
Returns JSON with: risk_level, overall_score (0-100), vulnerabilities[], vulnerability_count, best_practices_compliance, action_recommended, safe_to_deploy, audit_timestamp.
Workflow for Agent
- Load the user's config:
cat ~/.openclaw/openclaw.json - Run:
node SKILL_DIR/bin/shield.js audit ~/.openclaw/openclaw.json --summary - Present findings to user with prioritized recommendations
- Offer to sanitize before sharing:
node SKILL_DIR/bin/shield.js sanitize <file>
Files (agi-super-team)
-
.clawhub
-
origin.json 147 B
Loading…
-
-
bin
-
shield.js 5.2 KB
Loading…
-
-
scripts
-
shield-audit.sh 323 B
Loading…
-
-
src
-
audit.js 23 KB
Loading… -
sanitize.js 1.9 KB
Loading…
-
-
package.json 622 B
Loading… -
README.md 3.6 KB
# 🛡️ OpenClaw Shield **Security audit engine for OpenClaw configurations.** Find vulnerabilities, misconfigurations, and secret leaks before they become breaches. Built by [Autonomous Intelligence](https://autonomousintelligence.ai) — we run 9 agents in production. We know what breaks. ## Features - **11 security check categories** covering auth, networking, channels, agents, secrets, and more - **Structured JSON reports** with risk scores, severity levels, and remediation steps - **Config sanitizer** to strip secrets before sharing - **CLI tool** for quick audits - **Zero dependencies** — pure Node.js, no npm install needed ## Quick Start ```bash # Audit your live config node bin/shield.js audit ~/.openclaw/openclaw.json --summary # Get JSON report node bin/shield.js audit ~/.openclaw/openclaw.json # Strip secrets before sharing node bin/shield.js sanitize ~/.openclaw/openclaw.json > safe-config.json ``` ## Sample Output ``` ╔══════════════════════════════════════════════════╗ ║ 🛡️ OpenClaw Shield Audit Report ║ ╚══════════════════════════════════════════════════╝ Risk Level: HIGH Score: 42/100 Safe to Deploy: ❌ No Action: REVIEW_AND_REMEDIATE Vulnerabilities: 12 🔴 Critical: 2 🟠 High: 3 🟡 Medium: 4 🔵 Low: 3 ``` ## Security Checks | # | Category | What It Catches | |---|----------|----------------| | 1 | Gateway Auth | Missing auth token, insecure UI, weak tokens | | 2 | Network Exposure | Non-loopback bind, Tailscale funnel, wildcard proxies | | 3 | Channel Security | Wildcard allowFrom, missing allowlists | | 4 | DM Policy | Open DM policy without pairing | | 5 | Subagent Permissions | Wildcard allowAgents, circular chains, self-spawn | | 6 | Tool Permissions | Over-privileged agents (full tool access) | | 7 | Secret Leakage | API keys, tokens, private keys in plaintext | | 8 | Sandbox/Execution | Missing workspace isolation, no exec policies | | 9 | Plugin Config | Orphaned plugins, missing channel configs | | 10 | Heartbeat Exposure | Sensitive data in heartbeat prompts | | 11 | Remote Config | Unencrypted WebSocket, exposed remote tokens | ## JSON Report Schema ```json { "risk_level": "CRITICAL|HIGH|MEDIUM|LOW", "overall_score": 0-100, "vulnerabilities": [{ "category": "string", "severity": "critical|high|medium|low", "issue": "Description of the problem", "recommendation": "How to fix it", "auto_fix": { "path": "config.path", "value": "suggested_value" } }], "vulnerability_count": { "critical": 0, "high": 0, "medium": 0, "low": 0, "total": 0 }, "best_practices_compliance": 0.0-1.0, "action_recommended": "BLOCK|REVIEW_AND_REMEDIATE|APPROVE", "safe_to_deploy": true|false, "audit_timestamp": "ISO8601", "engine_version": "1.0.0" } ``` ## Programmatic Usage ```javascript const { auditConfig } = require('./src/audit'); const { sanitizeConfig } = require('./src/sanitize'); // Audit const config = require('./my-openclaw.json'); const report = auditConfig(config); if (!report.safe_to_deploy) { console.log(`${report.vulnerability_count.critical} critical issues found!`); } // Sanitize before sharing const clean = sanitizeConfig(config); ``` ## Pricing - **Local audit:** Free (install the skill, run locally) - **Premium remote audit:** $0.10/audit via ACP (deeper analysis + auto-fix patches) ## License MIT — Autonomous Intelligence 2026 -
SKILL.md 3.1 KB
--- name: openclaw-shield description: Security audit engine for OpenClaw configurations. Detects vulnerabilities, misconfigurations, secret leaks, and over-privileged agents. Use when the user asks about security, hardening, config review, or audit of their OpenClaw setup. metadata: {"openclaw":{"emoji":"🛡️","homepage":"https://github.com/autonomous-intelligence/openclaw-shield"}} --- # OpenClaw Shield — Security Audit Audit any OpenClaw config for security vulnerabilities, misconfigurations, and best-practice violations. Produces a structured JSON report with risk scores, findings, and remediation steps. ## When to Use - User asks to check/audit/review their OpenClaw security - User wants to harden their config before deploying - User is setting up a new OpenClaw instance - User asks about secret leakage or API key exposure in their config - Before publishing or sharing any config file ## Quick Audit (live config) ```bash node scripts/shield-audit.sh ``` Or directly: ```bash node SKILL_DIR/bin/shield.js audit ~/.openclaw/openclaw.json --summary ``` ## What It Checks (11 categories) 1. **Gateway Auth** — missing/weak auth, insecure UI settings 2. **Network Exposure** — bind address, Tailscale funnel, wildcard proxies 3. **Channel Security** — wildcard allowFrom, missing allowlists 4. **DM Policy** — open DM policy without pairing 5. **Subagent Permissions** — wildcard allowAgents, circular delegation chains, self-delegation 6. **Tool Permissions** — over-privileged agents with tools.profile: "full" 7. **Secret Leakage** — API keys, tokens, private keys in plaintext config 8. **Sandbox/Execution** — missing workspace isolation, no execution policies 9. **Plugin Config** — enabled plugins without channel config 10. **Heartbeat Exposure** — sensitive data in heartbeat prompts 11. **Remote Config** — unencrypted WebSocket, exposed remote URLs/tokens ## Usage ### Audit a config file ```bash node SKILL_DIR/bin/shield.js audit <config.json> node SKILL_DIR/bin/shield.js audit <config.json> --summary # human-readable ``` ### Audit from stdin ```bash cat config.json | node SKILL_DIR/bin/shield.js audit --stdin ``` ### Sanitize a config (strip secrets) ```bash node SKILL_DIR/bin/shield.js sanitize <config.json> ``` ### Programmatic use ```javascript const { auditConfig } = require('SKILL_DIR/src/audit'); const config = require('./openclaw.json'); const report = auditConfig(config); console.log(report.risk_level); // "CRITICAL" | "HIGH" | "MEDIUM" | "LOW" console.log(report.overall_score); // 0-100 console.log(report.vulnerabilities); // detailed findings ``` ## Output Returns JSON with: `risk_level`, `overall_score` (0-100), `vulnerabilities[]`, `vulnerability_count`, `best_practices_compliance`, `action_recommended`, `safe_to_deploy`, `audit_timestamp`. ## Workflow for Agent 1. Load the user's config: `cat ~/.openclaw/openclaw.json` 2. Run: `node SKILL_DIR/bin/shield.js audit ~/.openclaw/openclaw.json --summary` 3. Present findings to user with prioritized recommendations 4. Offer to sanitize before sharing: `node SKILL_DIR/bin/shield.js sanitize <file>` -
_meta.json 134 B
Loading…
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.