skillguard
Security scanner for OpenClaw/ClawHub skills. Detects malware, reverse shells, credential theft, prompt injection, memory poisoning, typosquatting, and suspicious prerequisites before installation. Use when installing new skills, auditing existing skills, checking a skill name for typosquatting, or scanning ClawHub skills for security risks.
Why use this skill?
Scan OpenClaw skills for malware, reverse shells, and credential theft. Protect your agent from malicious ClawHub threats today.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/msgnoki/skillguard-scannerWhat This Skill Does
SkillGuard is the essential security analysis engine for the OpenClaw ecosystem. Designed to act as a proactive gatekeeper, it performs deep-packet and code-level inspection on OpenClaw skills to identify malicious intent before execution. By monitoring for common threat vectors such as reverse shells, memory poisoning, and credential exfiltration, SkillGuard ensures that your autonomous agent environment remains uncompromised. It specifically targets the 'ClawHavoc' attack surface by validating prerequisites and detecting obfuscated code that seeks to hide malicious logic from standard human review.
Installation
To integrate SkillGuard into your OpenClaw environment, use the official repository command:
clawhub install openclaw/skills/skills/msgnoki/skillguard-scanner
Ensure that your OpenClaw environment has permissions to execute subprocess calls, as the scanner relies on Python-based analysis scripts to verify file integrity and network call patterns.
Use Cases
- Pre-Installation Auditing: Run a scan on any new skill fetched from ClawHub before allowing it to write to your
MEMORY.mdorSOUL.mdfiles. - Regular System Health Checks: Periodically scan all installed skills to detect drift or unauthorized changes that may have occurred during automated updates.
- Typosquatting Protection: Prevent 'Dependency Confusion' or 'Typosquatting' attacks by checking the integrity of skill names against the known OpenClaw registry before installation.
- Incident Response: If you suspect an agent is acting abnormally, use SkillGuard to audit recently installed skills for evidence of reverse shells or outbound data exfiltration.
Example Prompts
- "OpenClaw, please use skillguard to scan the 'web-browser-pro' skill I just downloaded from ClawHub before I install it."
- "Run a full security audit on all my current installed skills and show me a report of any high-risk flags."
- "Can you check if the skill name 'ai-assistant-tool' is a potential typosquatting attempt compared to the original?"
Tips & Limitations
SkillGuard works best when integrated into your automated workflow. While it is highly effective at catching known patterns, it is a heuristic-based scanner; always review 'MEDIUM' risk findings manually. Never ignore 'CRITICAL' alerts, as these almost always indicate malicious intent designed to compromise your local system shell or steal authentication tokens. Remember that it cannot verify the 'intent' of code if the malicious logic is completely obfuscated beyond standard heuristic detection; perform manual source code reviews for any skill requesting extensive file-system access or elevated network privileges.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-msgnoki-skillguard-scanner": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, code-execution