Return to Threats

Criminals are using ARTEX AI agents to speed up cyberattacks, FBI warns

Malwarebytes 2026-11-16 AI agent abuse Critical

Executive Summary

Attackers are reportedly using ARTEX AI agents to automate intrusions against organizations in several high-impact sectors. Security, risk, and technology leaders operating AI agents should evaluate agent authorization, monitoring, and abuse resistance.

What Happened

The FBI issued a November 13 advisory warning that attackers were abusing ARTEX, an authorized security-testing tool, to automate intrusions. Reported targets included finance, government, healthcare, and technology organizations.

Affected Products

  • ARTEX

Vulnerability / Attack Technique

AI-assisted automated intrusion

Technical Mechanism

The FBI advisory reportedly described attackers abusing ARTEX, an authorized security-testing tool, to automate intrusions. The article summary does not provide further technical details about the specific intrusion steps or ARTEX capabilities.

AI Security Category

AI-assisted attack

Part of the AI-Assisted Attacks topic.

Relevant Frameworks

LLM06:2025 Excessive AgencyMITRE ATLAS: ExecutionMITRE ATLAS: Initial Access

RealGround Analysis

AI agents that can execute security-testing or operational actions may increase the speed and scale of attacks when misused. Teams running AI agents or LLM applications should verify that agent permissions, tool access, and execution paths are constrained and monitored.

Recommended Controls

  • Apply least-privilege permissions to AI agents and restrict access to security-testing and intrusion-capable tools.
  • Require explicit authorization and human approval for high-impact agent actions.
  • Log and continuously monitor agent tool calls, targets, authentication context, and execution outcomes.
  • Perform adversarial red-team testing focused on agent misuse, unauthorized automation, and privilege escalation.
  • Implement rapid revocation and shutdown procedures for suspected agent compromise or abuse.

Related RealGround Service

AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.

Sources

Malwarebytes: https://www.malwarebytes.com/blog/ai/2026/11/criminals-are-using-artex-ai-agents-to-speed-up-cyberattacks-fbi-warns

Summary and analysis written by RealGround from the source above; last updated 2026-11-20.

Talk to AI CISO