AI Risk Wire

Cases › security breach › LR-2026-0885

ARTEX-driven autonomous intrusion campaign against cloud environments (Unit 42 observations)

Who did it
Outside attacker
AI agent used
ARTEX
How it was found
Third party
Reported
11 Nov 2026
Severity
Major
  1. Attackers used the autonomous ARTEX penetration testing framework to turn public password reset pages and exposed APIs into a route to cloud access. They then used the associated credentials and trust relationships to reach the cloud.
  2. Attackers used ARTEX to gain cloud access through internet-exposed identity workflows and APIs, abusing credentials and trust relationships. No software vulnerability was exploited.
  3. A coordinated ARTEX campaign targeted customer cloud environments in sectors worldwide, including retail and consulting. The activity was seen across multiple organizations and sectors.
  4. Unit 42's Incident Response team investigated intrusions where the attacker's server hosted an ARTEX console or used associated infrastructure and user agents. Its Managed Threat Hunting team also tracked the campaign.

Source: Unit 42

What was done

The ARTEX author made the repository closed-source and ceased public development to prevent misuse.

Withdrawn or disabled (Other) · Withdrawn or disabled (Developer or vendor)

Fix reported: “The ARTEX author made the repository closed-source and ceased public development to prevent misuse.”

Risks AI system attacked or breached (54 incidents)

No source states: AI company and model, money lost or records, tools it had, company using the AI, sector.

Evidence

Sources (1)

  1. ARTEX and AI-Powered Red Teaming Tools: What Defenders Need to Know · Unit 42 · 2026-11-11
Show every field, with its source and grade

The AI system

Software around the model
ARTEX
C one secondary source states it
What it was for
red teaming and penetration testing
C one secondary source states it

What happened

Earliest source we hold
2026-11-11
D inferred by us from the described behaviour, reason shown
Who caught it
an outside party
D inferred by us from the described behaviour, reason shown
Who caused it
an outside attacker
D inferred by us from the described behaviour, reason shown
What was done
The ARTEX author made the repository closed-source and ceased public development to prevent misuse.
D inferred by us from the described behaviour, reason shown
What went wrong
security breach
D inferred by us from the described behaviour, reason shown
AI agent
an AI agent acted
C one secondary source states it

Impact

Severity
major
D inferred by us from the described behaviour, reason shown
Why this severity
Activity was observed across multiple organizations and sectors, with live cloud environments of customers targeted worldwide, which indicates many third parties and live production compromise.
D inferred by us from the described behaviour, reason shown

LR-2026-0885 · version 2 · published 2026-11-12 after automatic checks; not yet checked field by field by a person