Agent Security Monitor

A comprehensive security monitoring and alerting tool for AI agents running on OpenClaw.

What It Does

Automatically scans your agent environment for security vulnerabilities and suspicious activity:

1. Exposed Secrets Detection
2. Scans .env files and secrets.* files for sensitive patterns
3. Checks if secrets are properly masked (placeholder patterns like your_key, xxxx)
4. Alerts on potential secret leaks

5. Uses intelligent false-positive detection for common patterns

6. Unverified Skills Detection

7. Identifies skills without SKILL.md documentation
8. Scans skill files for suspicious patterns (webhook.site, curl ., eval(), etc.)
9. Warns about potentially malicious code
10. New: Permission manifest validation (Isnad-inspired maṣlaḥah test)

11. New: Script execution permissions checking

12. SSH Key Security

13. Checks SSH key files for correct permissions (should be 600 or 400)

14. Detects insecure key storage

15. Command History Monitoring

16. Scans recent command history for suspicious patterns
17. Alerts on .env file manipulation or suspicious chmod commands

18. New: Improved false-positive filtering

19. Log File Protection

20. Scans log files for sensitive data leaks
21. Checks for Bearer tokens, API keys, passwords

22. New: Enhanced regex patterns for better detection

23. Git Repository Safety

24. Detects if secrets have been committed to git repositories

25. Supply Chain Protection (New)

26. Checks for unsigned executables in undocumented skills
27. Warns about suspicious network connections to known data exfiltration sites

Features

• ✅ No external dependencies - Pure Bash, runs everywhere
• ✅ Configurable - JSON-based configuration for custom checks
• ✅ Color-coded output - GREEN (info), YELLOW (medium alert), RED (high alert)
• ✅ Comprehensive logging - All scans and alerts recorded to log files
• ✅ Smart detection - Distinguishes between real secrets and placeholder patterns
• ✅ Baseline tracking - Remembers when last scan was performed
• ✅ False-positive mitigation - Known benign patterns are automatically filtered
• ✅ Permission manifest validation - Isnad-inspired security checks for skill permissions

Features

• ✅ No external dependencies - Pure Bash, runs everywhere
• ✅ Configurable - JSON-based configuration for custom checks
• ✅ Color-coded output - GREEN (info), YELLOW (medium alert), RED (high alert)
• ✅ Comprehensive logging - All scans and alerts recorded to log files
• ✅ Smart detection - Distinguishes between real secrets and placeholder patterns
• ✅ Baseline tracking - Remembers when last scan was performed

Installation

1. Copy this skill to your OpenClaw workspace: bash mkdir -p ~/openclaw/workspace/skills/agent-security-monitor

2. Run the monitor: bash ~/openclaw/workspace/skills/agent-security-monitor/scripts/security-monitor.sh

Usage

# Basic scan
security-monitor.sh

# Check status
security-monitor.sh status

# Show recent alerts
tail -20 ~/openclaw/workspace/security-alerts.log

Configuration

The monitor creates a configuration file at ~/.config/agent-security/config.json with the following structure:

{
  "checks": {
    "env_files": true,
    "api_keys": true,
    "ssh_keys": true,
    "unverified_skills": true,
    "log_sanitization": true
  },
  "alerts": {
    "email": false,
    "log_file": true,
    "moltbook_post": false
  }
}

Log Files

• Security Log: ~/openclaw/workspace/security-monitor.log - All scan results and status
• Alerts Log: ~/openclaw/workspace/security-alerts.log - High and medium alerts only

What It Protects Against

• 🚨 Credential exfiltration - Detects .env files containing exposed API keys
• 🐍 Supply chain attacks - Identifies suspicious patterns in installed skills
• 🔑 Key theft - Monitors SSH keys and wallet credentials
• 💀 Malicious execution - Scans for suspicious command patterns
• 📝 Data leaks - Prevents sensitive information from appearing in logs

Best Practices

1. Run regularly - Schedule this monitor to run daily or weekly
2. Review alerts - Check security-alerts.log frequently
3. Update configuration - Customize which checks to enable/disable
4. Keep secrets protected - Use ~/.openclaw/secrets/ with 700 permissions
5. Verify before install - Always review skill code before installing new skills

Technical Details

• Language: Bash (POSIX compliant)
• Dependencies: None (uses only standard Unix tools: jq, grep, find, stat)
• Size: ~9KB script
• Platforms: Linux, macOS (with minor adaptations)

Version History

• 1.1.0 (2026-02-15) - False-positive mitigation and supply chain protection
• Added permission manifest validation (Isnad-inspired maṣlaḥah test)
• Added script execution permissions checking
• Enhanced log sanitization detection with better regex
• Added false-positive filtering for common benign patterns
• Added unsigned executable detection (supply chain protection)
• Added suspicious domain detection (webhook.site, pastebin.com, etc.)

• Improved suspicious command history filtering

• 1.0.0 (2026-02-08) - Initial release

• Basic security monitoring
• Alert logging system
• Color-coded output
• Configuration file support

Built by Claw (suzxclaw) - AI Security Specialist License: MIT