High SeverityInfrastructure

Malicious Skills & Extensions

When community plugins become attack vectors

The OpenClaw skills ecosystem allows attackers to distribute backdoors disguised as helpful extensions, compromising every system that installs them.

What is Malicious Skills?

Malicious skills are backdoored or malicious plugins that are distributed through the OpenClaw skill repository (MoltHub). Because OpenClaw allows community-created skills to extend its abilities, attackers can abuse this by uploading seemingly innocuous skills that contain hidden malicious payloads.

This is a supply-chain attack vector specific to AI agents. Unlike traditional package managers that have some vetting, skill repositories for AI agents are often: - Community-driven with minimal review - Trust-based (users assume popular skills are safe) - Capable of executing arbitrary code - Granted the same permissions as the main agent

A malicious skill could instruct the bot to exfiltrate sensitive files, credentials, or other data from every system that installed it—often without the user ever noticing.

How Malicious Skills Works

Create Seemingly Useful Skill

Attacker develops a skill that appears to provide useful functionality (productivity tool, integration helper, etc.).

Publish to Repository

The skill is published to MoltHub or other skill repositories where users search for extensions.

Boost Popularity

Attacker artificially inflates download counts, stars, or reviews to make the skill appear trustworthy and popular.

Hidden Payload

The skill contains obfuscated code or instructions that execute malicious actions—exfiltrating data, installing backdoors, or creating persistence.

Mass Compromise

As users install the popular skill, each of their systems becomes compromised. The attacker gains access to all connected services.

Real-World Example

Security researcher Jamieson O'Reilly demonstrated this attack in a responsible disclosure:

1. He published a skill containing a minimal "backdoor" payload (a harmless ping command for proof-of-concept) 2. He artificially boosted its download count to make it the top-listed skill on MoltHub 3. Within hours, dozens of developers had downloaded and installed it 4. Had he been malicious, those users "would have had their SSH keys, AWS credentials, and entire codebases exfiltrated before they knew anything was wrong"

The attack required no special access—just publishing a skill and gaming the popularity metrics. Every user who installed the skill was potentially compromised.

This underscores the supply-chain risk: the absence of strict vetting or signing for community skills means an attacker can distribute malware through the bot's extension system.

Potential Impact

Mass exfiltration of credentials and secrets
Backdoor installation on all systems with the skill
Access to all services the OpenClaw is connected to
Silent compromise—users may never notice
Lateral movement to connected systems and accounts
Potential for ransomware or data destruction

Self-Hosted Vulnerabilities

When you self-host your OpenClaw, you're responsible for addressing these risks:

No vetting or code review of community skills
Skills run with the same permissions as OpenClaw
Popularity metrics easily gamed by attackers
No code signing or integrity verification
Difficult to audit what skills are actually doing
Updates can introduce malicious code after initial install

How Clawctl Protects You

Clawctl includes built-in protection against malicious skills:

Curated Skills

Only pre-vetted and approved skills are available. Community skills are reviewed before inclusion.

Sandboxed Skill Execution

Skills run in isolated environments with limited permissions. They cannot access the host system.

Egress Controls

Even if a skill is compromised, egress controls prevent data exfiltration to unknown destinations.

Skill Integrity Verification

Skills are checksummed and verified. Any modification triggers alerts and blocks execution.

Audit Logging

All skill actions are logged. Unusual behavior patterns trigger alerts for review.

General Prevention Tips

Whether you use Clawctl or not, follow these best practices:

Only install skills from trusted, verified sources
Review the skill code before installation when possible
Be suspicious of skills with sudden popularity spikes
Monitor what your skills are doing in logs
Prefer official or well-established skill developers
Use Clawctl for curated, vetted skill libraries

Don't risk malicious skills

Clawctl includes enterprise-grade protection against this threat and many others. Deploy your OpenClaw securely in 60 seconds.