← Back to Articles
// Threat Intelligence Report

OpenClaw (ClawdBot / Moltbot) Vulnerability Assessment

Paul Holder February 6, 2026 TLP:CLEAR MITRE ATT&CK Mapped
Overall Risk
CRITICAL
Exploitation Status
ACTIVELY EXPLOITED
Affected Users
60,000+

1. Executive Summary

OpenClaw (formerly ClawdBot, briefly Moltbot) is an open-source autonomous AI agent framework that exploded to 30,000+ GitHub stars in January 2026. Created by Peter Steinberger, founder of PSPDFKit/Nutrient, the project enables AI-powered personal assistants that operate directly on user hardware with full system access, including filesystem control, browser automation, shell command execution, and integration with messaging platforms.

This report documents the critical security vulnerabilities, active exploitation patterns, and supply chain compromise vectors identified in the OpenClaw ecosystem between January and February 2026. The findings represent what security researchers are calling the first major wave of AI-agent abuse in the wild, establishing a new exploitation class where threat actors weaponize trust in autonomous AI tooling.

Key Findings

Finding 01

Remote Code Execution

CVE-2026-25157 and CVE-2026-25253: Critical RCE vulnerabilities enabling one-click remote compromise of host systems.

Finding 02

Plaintext Credential Storage

API keys, authentication tokens, user profiles, and conversation memories stored in unencrypted Markdown and JSON files.

Finding 03

Supply Chain Compromise

Malicious VS Code extensions deploying trojans and RATs. Hundreds of malicious skills identified in the ClawHub repository.

Finding 04

Authentication Bypass

Gateway localhost handling flaw allows external attackers to bypass login when behind Nginx reverse proxy.

Finding 05

Indirect Prompt Injection

The agent's ability to read emails and messages creates attack surfaces for unauthorized command injection.

Finding 06

Social Engineering via Trademark Chaos

During the Clawdbot-to-Moltbot rename, threat actors hijacked @clawdbot handles to promote fraudulent $CLAWD tokens to 60,000+ followers.

2. Threat Landscape Analysis

Vulnerability Summary

Vulnerability Severity CVE ATT&CK ID Status
Remote Code Execution Critical CVE-2026-25157 T1203 Patched (2026.1.29)
RCE via Exploitation Critical CVE-2026-25253 T1203 Patched (2026.1.30)
Plaintext Credential Storage High N/A T1552 Design Flaw (Unresolved)
Authentication Bypass High N/A T1556 Partially Mitigated
Exposed Control Interface High N/A T1133 User Misconfiguration
Malicious Skills (Supply Chain) High N/A T1195.002 Ongoing
Fake VS Code Extensions High N/A T1195.002 Active Threat
Indirect Prompt Injection Medium N/A T1059 Architectural Limitation
Crypto Scam (Handle Hijack) Medium N/A T1598 Active Threat

3. MITRE ATT&CK Framework Mapping

3.1 Initial Access

Technique IDTechniqueOpenClaw Context
T1133External Remote ServicesUnsecured control interfaces discovered publicly accessible via Shodan scanning
T1195.002Supply Chain: SoftwareMalicious skills in ClawHub + fake VS Code extensions delivering trojans
T1598Phishing: Software DependenciesFake repos, domain typosquatting, hijacked social handles for crypto scams

3.2 Execution

Technique IDTechniqueOpenClaw Context
T1203Exploitation for Client ExecutionCVE-2026-25253: One-click RCE for full system compromise
T1059Command and Scripting InterpreterSkills execute local scripts with full OS permissions; prompt injection triggers unauthorized execution
T1609Abuse of Trusted RelationshipsFake VS Code extension leverages developer trust in marketplace

3.3 Persistence and Credential Access

Technique IDTechniqueOpenClaw Context
T1552Unsecured CredentialsAPI keys, tokens stored in plaintext Markdown/JSON files
T1556Modify Authentication ProcessLocalhost handling flaw bypasses auth behind Nginx

3.4 Collection and Exfiltration

Technique IDTechniqueOpenClaw Context
T1071.001Application Layer Protocol: WebWebSocket backdoors blending with legitimate agent traffic
NovelCognitive Context TheftExfiltration of persistent memory and conversation histories

4. Attack Chain Reconstruction

4.1 Primary Kill Chain: Exposed Gateway to Full Compromise

Stage 1: Reconnaissance
Scan for exposed OpenClaw Control interfaces
Shodan queries reveal publicly accessible instances
Stage 2: Initial Access
Exploit localhost bypass (T1556)
Authentication flaw when deployed behind Nginx reverse proxy
Stage 3: Credential Harvesting
Access plaintext credential files (T1552)
API keys, tokens, and auth data stored unencrypted
Stage 4: Execution
Leverage agent's shell access for arbitrary commands
Full OS-level control through the agent's own capabilities
Stage 5: Cognitive Context Theft
Extract memory files and conversation histories
Novel attack vector: behavioral patterns and decision-making exposed
Stage 6: Persistence
Install malicious skills or modify SOUL.md
Backdoor access through the agent's own configuration system

4.2 Secondary Kill Chain: Supply Chain Compromise

Stage 1: Preparation
Create malicious skill or fake VS Code extension
Weaponized packages designed to appear legitimate
Stage 2: Distribution
Publish to community or VS Code marketplace
Leveraging marketplace trust for wide distribution
Stage 3: Installation
User installs, granting full OS-level permissions
No sandboxing between agent capabilities and host system
Stage 4: Execution
Full system compromise via trusted execution context
Agent's own permission set used against the user

5. Emerging Threat Category: AI Agent Abuse

The OpenClaw incidents establish a new threat category: autonomous AI agent abuse. The defining characteristics are:

Organizations must incorporate autonomous AI agent threat modeling into security frameworks. Evaluate deployments against: principle of least privilege enforcement, credential isolation and encryption, action logging with anomaly detection, supply chain verification, and network segmentation.

6. Indicators of Compromise

TypeIndicatorContext
VS Code Extensionclawdbot.clawdbot-agentMalware delivery (trojan + RAT)
CVECVE-2026-25157Remote Code Execution
CVECVE-2026-25253One-click remote compromise
Social Media@clawdbot (X/GitHub)Crypto scam ($CLAWD token)
NetworkExposed Control interfacesShodan-discoverable, no auth
File PatternObfuscated shell scriptsSupply chain payload delivery
CWECWE-400 (SSE client)Denial of service vector

7. Hardening Recommendations

7.1 Immediate Actions (Critical)

7.2 Organizational Policy

8. Conclusion

The OpenClaw/ClawdBot incident sequence represents a critical inflection point in AI security. The speed of compromise, from project launch to active CVE exploitation to supply chain poisoning in under six weeks, should serve as a warning to any organization evaluating autonomous AI agent deployment.

The fundamental tension at the heart of AI agent design is that usefulness requires access, and access creates risk. Organizations that begin building AI agent security capabilities now will be positioned to safely leverage productivity benefits while managing inherent risks.

9. References

1. Tenable. "Agentic AI Security: How to Mitigate Clawdbot/Moltbot/OpenClaw Vulnerabilities." February 3, 2026.

2. CNBC. "From Clawdbot to Moltbot to OpenClaw." February 2, 2026.

3. Security Boulevard. "Critical Vulnerabilities and 6 Immediate Hardening Steps." February 3, 2026.

4. Bolen, S. "OpenClaw: When the AI With Hands Becomes a Digital Minefield." RONIN OWL CTI, February 2026.

5. MITRE ATT&CK Enterprise Framework v14. The MITRE Corporation, 2025.

6. OpenClaw GitHub Repository. github.com/openclaw/openclaw.

7. SlowMist Security Advisory. OpenClaw Deployment Misconfiguration Analysis, January 2026.

Protect Your Business

Not sure how AI agents and tools like this affect your security? Book a 1-on-1 Business Security Checkup. 60 minutes, personalized risk report, actionable plan.

Book a Security Checkup - $250

About the Author

Paul Holder is a Cybersecurity Professional and AI Security Researcher with a B.Tech in Computer Engineering and 8+ years of technical experience spanning development, security automation, and AI systems. His work focuses on threat modeling for emerging AI technologies, MITRE ATT&CK-based vulnerability assessment, and developing security frameworks for organizations navigating the autonomous AI agent landscape.

He is the author of Stay Smart, Stay Safe, available on Amazon.

paulholder.com | LinkedIn | GitHub