Execution via OpenClaw Agent

Last updated 9 days ago on 2026-02-02
Created 9 days ago on 2026-02-02

About

Detects suspicious child process execution from the OpenClaw, Moltbot, or Clawdbot AI coding agents running via Node.js. These tools can execute arbitrary shell commands through skills or prompt injection attacks. Malicious skills from public registries like ClawHub have been observed executing obfuscated download-and-execute commands targeting cryptocurrency wallets and credentials. This rule identifies shells, scripting interpreters, and common LOLBins spawned by these AI agents.
Tags
Domain: EndpointDomain: LLMOS: LinuxOS: macOSOS: WindowsUse Case: Threat DetectionTactic: ExecutionTactic: Command and ControlData Source: Elastic DefendLanguage: eql
Severity
medium
Risk Score
47
MITRE ATT&CK™

Execution (TA0002)(external, opens in a new tab or window)

Command and Control (TA0011)(external, opens in a new tab or window)

License
Elastic License v2(external, opens in a new tab or window)

Definition

Rule Type
Event Correlation Rule
Integration Pack
Prebuilt Security Detection Rules
Index Patterns
logs-endpoint.events.process-*
Related Integrations

endpoint(external, opens in a new tab or window)

Query
text code block:
process where event.type == "start" and process.parent.name : ("node", "node.exe") and process.parent.command_line : ("*openclaw*", "*moltbot*", "*clawdbot*") and process.name : ("bash", "sh", "zsh", "bash.exe", "cmd.exe", "powershell.exe", "curl.exe", "curl", "base64", "xattr", "osascript", "python*", "chmod", "certutil.exe", "rundll32.exe")

Install detection rules in Elastic Security

Detect Execution via OpenClaw Agent in the Elastic Security detection engine by installing this rule into your Elastic Stack.

To setup this rule, check out the installation guide for Prebuilt Security Detection Rules(external, opens in a new tab or window).