AI Risk Wire

Cases › security breach › LR-2026-0824

ARTEX multi-agent framework used by attackers to automate Active Directory compromise

Preliminary Why: 1 report: Cyber Security News · subject to change · 1 independent report

Developing: a major or severe case captured in the last 72 hours. Later changes are logged on the corrections page.

Status: no action reported

Severity major
Reported 2 Nov 2026
Agent tool ARTEX
Could do powershell, credential access, kerberos ticket requests, dcsync, lateral movement, web shell planting

No source states: loss or records, developer and model, deployer, industry.

Severity major: a live production compromise across multiple victim organizations in several sectors, with domain controller hashes and the krbtgt key taken.

Attackers used ARTEX, an open-source multi-agent penetration-testing and command-and-control platform written in Go, to automate network break-ins. The attacker supplied a goal and stolen credentials, and the framework split the work across six sub-agents that ran PowerShell against domain controllers and federation servers, enumerated managed service accounts and AD CS templates, pulled more than 110,000 Active Directory objects, performed Kerberoasting, and ran DCSync to take the krbtgt key, cloud sync credentials and domain controller hashes. It then attempted lateral movement via Pass-the-Ticket, WinRM, Kerberos relay and Pass-the-Hash; Windows service token limits and endpoint protection blocked some attempts before defenders cut off the server. Google Threat Intelligence Group and Mandiant identified the activity during incident response, seeing use since late August 2026 against government, technology, chemicals, manufacturing and telecommunications organizations.

What happened

No source tells the story step by step yet.

What was done

No source states an action or fix.

Risks

AI used to run a cyber attack
Also
88 incidents
Rising: 25 vs 3.8 a week

Sorted by rule from the case's fields; not yet read from the sources.

Controls

Not yet read for controls. Controls that mitigate the primary risk:

Application

Short-lived, scoped credentials · Secrets kept out of the model's context · Separate identity for each agent · Least-privilege access for the agent · Alerts on unusual tool use · Activity logs · Sensitive-data checks on outbound data

Infrastructure / target

Multi-factor sign-in and password policy · Secrets scanning

Similar incidents

All cases of this kind ›

Evidence

No source states: a step-by-step account, when it happened, when it was found, how many records were exposed, the direct loss, a count of the other parties affected, any court case, the cause, what set it off, what was done.

Show every field, with its source and grade

The AI system

Software around the model
ARTEX
C one secondary source states it
Tools it was given
powershell, credential access, kerberos ticket requests, dcsync, lateral movement, web shell planting
C one secondary source states it
Stage of use
in live use
C one secondary source states it
How it was connected
agent with tools
C one secondary source states it
What it was for
multi-agent penetration testing and command-and-control platform
C one secondary source states it

What happened

Earliest source we hold
2026-11-02
D inferred by us from the described behaviour, reason shown
Who caught it
an outside party
C one secondary source states it
Themes
agentic AI, multi-agent, credential theft, kerberoasting, dcsync, lateral movement, AI assisted cyberattack
C one secondary source states it
Who caused it
an outside attacker
C one secondary source states it
What went wrong
security breach
C one secondary source states it
AI agent
an AI agent acted
C one secondary source states it
What it did
The agent was handed valid stolen logins and used them to run the later attack stages, including DCSync extraction of the krbtgt key and domain controller hashes.
C one secondary source states it

Impact

Severity
major
C one secondary source states it
Kind of harm
others' security, operations
C one secondary source states it
Who was affected
organizations in government, technology, chemicals, manufacturing, and telecommunications
C one secondary source states it
Kinds of data exposed
credentials
C one secondary source states it
Why this severity
a live production compromise across multiple victim organizations in several sectors, with domain controller hashes and the krbtgt key taken.
C one secondary source states it

Notes on gaps

No monetary figures are given in any currency. Extractor proposed values without quotes; dropped: .

LR-2026-0824 · version 1 · published 2026-11-03 after automatic checks; not yet checked field by field by a person · JSON