What is Moltbot / ClawdBot?
Moltbot (formerly branded as ClawdBot) is an AI personal assistant designed to operate through popular messaging platforms like WhatsApp and Telegram. It provides users with AI-powered assistance for various tasks, from answering questions to executing automated workflows through its extensible "skill" system.
Platform Characteristics
WhatsApp, Telegram bots
Extensible via ClawdHub
HTTP console (port 8080)
Local Markdown/JSON files
While the concept of AI assistants accessible via messaging apps is appealing for convenience, the security posture of many Moltbot deployments has been found to be severely lacking, creating significant enterprise risk.
Critical Security Issues Identified
1. Unauthenticated Admin Ports
Researchers discovered hundreds of Moltbot instances exposing unauthenticated admin ports to the internet. The default HTTP console on port 8080 often lacks any authentication, allowing anyone to access administrative functions.
[+] Moltbot started listening on 0.0.0.0:8080 — "exposed to the web"2. Plaintext Credential Storage
User credentials and secrets are written to plaintext Markdown and JSON files. This makes them trivial targets for commodity infostealers like RedLine, Lumma, and Vidar that specifically scan for credential files.
~/.moltbot/credentials.md~/.moltbot/config.json3. Supply-Chain Skill Poisoning
The skill library (ClawdHub) can be poisoned with malicious skills. A proof-of-concept attack demonstrated uploading a malicious skill that achieved remote command execution on all downstream users who installed it.
4. Unsafe Proxy Configurations
Many deployments were found with unsafe proxy configurations that could be leveraged to pivot through the network, exfiltrate data, or establish persistent backdoor access.
Threat Actor Capabilities
By exploiting these vulnerabilities, threat actors gain significant capabilities:
Steal Secrets
API keys, passwords, tokens from plaintext storage
Exfiltrate Code
Access and steal source code repositories
Deploy Backdoors
Repurpose the assistant as persistent access
C2 Operations
Use as command-and-control infrastructure
Infostealers Targeting Moltbot Credentials
Because Moltbot stores secrets in plaintext files, it has become a target for commodity infostealers that automatically scan for and exfiltrate credential files:
RedLine Stealer
Widely distributed MaaS that targets browser data, crypto wallets, and now Moltbot configs.
Lumma Stealer
Modern infostealer with extensive file-grabbing capabilities targeting plaintext secrets.
Vidar Stealer
Popular stealer-as-a-service known for credential harvesting from various applications.
Detection Rules & Indicators
SOC Prime has released multiple Sigma rules for detecting Moltbot-related activity:
Simulation Script
The following PowerShell script simulates Moltbot deployment for detection testing:
# ----------------------------------------------------
# Moltbot Exposure Simulation – PowerShell
# ----------------------------------------------------
# 1. Create a temporary directory
$tempDir = "$env:TEMP\MoltbotSim"
New-Item -ItemType Directory -Force -Path $tempDir | Out-Null
# 2. Simulate downloading a Moltbot executable (placeholder)
$molExe = "$tempDir\moltbot.exe"
Invoke-WebRequest -Uri "https://example.com/moltbot.exe" \
-OutFile $molExe -UseBasicParsing
# 3. Run Moltbot with default (exposed) settings
$proc = Start-Process -FilePath $molExe \
-ArgumentList "--listen 0.0.0.0:8080" \
-PassThru -WindowStyle Hidden
Write-Host "[+] Moltbot started (PID: $($proc.Id)) on 0.0.0.0:8080"
# 4. Wait for service registration in logs
Start-Sleep -Seconds 5
# 5. Simulate external connection
Try {
Invoke-WebRequest -Uri "http://$($env:COMPUTERNAME):8080" \
-UseBasicParsing -TimeoutSec 5
Write-Host "[+] External HTTP request sent to Moltbot UI."
} Catch {
Write-Warning "[-] Unable to reach Moltbot UI."
}
# 6. Cleanup
Stop-Process -Id $proc.Id -Force
Remove-Item -Recurse -Force $tempDir
Write-Host "[+] Simulation completed and cleaned up."Mitigation Strategies
Access Control
Data Protection
Supply Chain Security
Monitoring & Response
Incident Response Playbook
If Compromise is Confirmed:
- 1Isolate the affected system immediately
- 2Revoke all exposed credentials and API keys
- 3Audit all skill installations for malicious content
- 4Validate integrity of stored configuration files
- 5Check for lateral movement indicators
- 6Redeploy Moltbot with hardened security settings
- 7Implement continuous monitoring going forward
Research Attribution
This analysis is based on threat intelligence from SOC Prime's Threat Detection Marketplace and research published by their threat research team.
Protect Your Infrastructure
Use PROXIES.SX mobile proxies to test your security posture from different network perspectives. Identify exposed services before threat actors do.