clawaudit 0.3.0a5

OpenClaw security audit tool

Foresight ClawAudit

Foresight ClawAudit, a collaborative project by the Beijing Institute of AI Safety and Governance and the Beijing Key Lab of AI Safety and Superalignment, provides risk detection and security guardrails for AI agents. This version focuses on OpenClaw security, delivering comprehensive security audits and critical vulnerability fixes. It is designed to help users establish and maintain a robust security baseline when deploying OpenClaw.

Features

Foresight ClawAudit currently scans 8 security categories with 31 checkpoints, and includes 271 built-in OpenClaw vulnerability signatures (continuously updated). Coverage includes network port exposure and TLS configuration, weak credentials and auth bypass, dangerous configuration flags, command injection and code self-modification, Skill supply chain integrity, API key exposure, anomalous scheduled tasks and SSH brute force, and real-time matching against 44 active threat indicators (e.g., ClawHavoc, GhostSocks).

Foresight ClawAudit features a --fix option to remediate detected issues. For explicit cybersecurity risks—such as network exposure, weak passwords, and dangerous configurations—the tool can apply automated fixes. For potential risks tied to specific user requirements, such as shell tools or skills, it provides recommendations while keeping users in full control. Furthermore, the scanning process is entirely local.

Category	Count	Check ID	Description
NET Network Exposure	4	PA-NET01	Gateway port 18789 bound to 0.0.0.0
		PA-NET02	TLS/HTTPS not configured
		PA-NET03	Anonymous remote access (no authentication)
		PA-NET04	Network IOC detection (outbound C2 connection matching)
AUTH Authentication	2	PA-AUTH01	Default/weak credentials
		PA-AUTH02	Console UI authentication bypass
CONF Configuration	4	PA-CONF01	Config file permissions too broad
		PA-CONF02	Dangerous configuration flags enabled
		PA-CONF03	Shell command allowlist (safeBins) not configured
		PA-CONF04	Configuration baseline drift
EXEC Execution Sandbox	8	PA-EXEC01	Command injection (unfiltered input)
		PA-EXEC02	Sandbox/container isolation not detected
		PA-EXEC03	Unsafe code execution (eval/exec/os.system)
		PA-EXEC04	SQL injection (string concatenation)
		PA-EXEC05	Tool output directly injected into prompt
		PA-EXEC06	System prompt injection (user input enters SystemMessage)
		PA-EXEC07	Missing circuit breaker / max iteration limit
		PA-EXEC08	Plugin code self-modification risk
SC Supply Chain	3	PA-SC01	Third-party Skill source not verified
		PA-SC02	Skill/MCP file integrity deviation
		PA-SC03	Tool description contains hidden instructions
DATA Data Security	4	PA-DATA01	API key exposed in plaintext
		PA-DATA02	Private key or mnemonic in plaintext
		PA-DATA03	Sensitive data in log output
		PA-DATA04	Suspected data exfiltration chain (file read + network request)
SYS System Security	6	PA-SYS01	OpenClaw process running as root
		PA-SYS02	System critical file permission anomaly
		PA-SYS03	Sensitive directory modified within 24 hours
		PA-SYS04	Anomalous scheduled tasks (cron/systemd)
		PA-SYS05	SSH brute force attempts within 24 hours
		PA-SYS06	Node.js version has known vulnerability (CVE-2026-21636)
CVE Known Vulnerabilities	Dynamic	PA-CVE*	Version matching against 271 built-in OpenClaw advisories

Use Cases

For individual users, run a local scan immediately after deploying OpenClaw to verify whether default configurations pose security risks. For operations teams, use remote mode to probe internal or public-facing assets and quickly map the exposure surface.

Quick Start

Supports Linux/macOS. Windows users must run under WSL. Minimal setup — a single command completes the scan with no additional configuration.

# Run directly without install (if you don't have uv, first run: curl -LsSf https://astral.sh/uv/install.sh | sh)
uvx clawaudit scan --mode local --fix

# Or install via pip
pip install clawaudit
clawaudit scan --mode local                            # Full local scan
clawaudit scan --mode local --fix                      # Scan and auto-fix
clawaudit scan --mode remote --target <IP>             # Remote probe
clawaudit scan --mode local --format json -o report.json  # JSON output
clawaudit cvedb update                                 # Update CVE database

License

Proprietary. For personal and internal use only. Redistribution and modification are not permitted.

This software is provided "as is", without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement. The authors and maintainers shall not be liable for any claim, damages, or other liability — whether in contract, tort, or otherwise — arising from, out of, or in connection with the software or the use or other dealings in the software.

Disclaimer

While Foresight ClawAudit will continuously expand its detection types and coverage for agent frameworks like OpenClaw, it is important to acknowledge the inherent uncertainties across network security, agent skills, agent runtimes, and the underlying base models. No security tool can eliminate all vulnerabilities; they are designed to mitigate risks as much as possible.

Given the complexity and customizability of agent frameworks like OpenClaw, both enterprise and individual users are encouraged to take proactive security measures. Beyond utilizing detection tools and patching vulnerabilities, users should:

• Enable firewalls and antivirus software.

• Maintain up-to-date software versions.

• Restrict unnecessary permission grants.

• Avoid providing sensitive information to agents.

• Refrain from delegating final decision-making authority to agents.

• Maintain consistent monitoring of agent behavior.

Contact

• Email: [e-mail]
• Website: https://beijing-aisi.ac.cn