Not classifiedARTEXPentAGI

GTIG/Mandiant: UNC7228 and other crews run ARTEX and PentAGI agent frameworks in live intrusions at machine speed

Google's incident responders have seen ARTEX and PentAGI agents run lateral movement, AD credential theft, webshell deployment and exfil prep on their own after operators hand them credentials, with…

What happened

Google's incident responders have seen ARTEX and PentAGI agents run lateral movement, AD credential theft, webshell deployment and exfil prep on their own after operators hand them credentials, with access-to-deep-access times as short as 15 minutes.

Read the original sourceAdditional source: cellcog.ai

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A summary diagram derived from the entry fields, not a verified detailed sequence. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Reported initial access

    unknown

    Source for step 1
  2. 02 · Reported activity

    Google's incident responders have seen ARTEX and PentAGI agents run lateral movement, AD credential theft, webshell deployment and exfil prep on their own after operators hand them credentials, with access-to-deep-access times as short as 15 minutes.

    Source for step 2
  3. 03 · AI involvement

    ARTEX, PentAGI, Hexstrike, CAIRN agent frameworks · unnamed frontier and open-weight LLM APIs, LLM mixers and local models

    Source for step 3

Why it matters

Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Government; Technology and AI companies; Critical infrastructure; Multiple sectors; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Prevention guidance has not been recorded for this entry. Review the original report for available mitigations.

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance Additional source 2
Technical detailsTooling, impact

Attack context

AI's role
AI as operator
Offensive frameworks
ARTEXPentAGI

Tooling as reported

AI products, models and artifacts

  • ARTEX, PentAGI, Hexstrike, CAIRN agent frameworksCommunity-maintained fork; the original repository is unavailable.
  • unnamed frontier and open-weight LLM APIs, LLM mixers and local models

Targets and reported impact

Targets / sectors
Government; Technology and AI companies; Critical infrastructure; Multiple sectors

Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.

Reported attribution

UNC7228 (GTIG; overlaps Microsoft's Storm-0940); other unnamed financially motivated and suspected PRC-nexus clusters

Structured attribution

Actor
UNC7228 (GTIG; overlaps Microsoft's Storm-0940); other unnamed financially motivated and suspected PRC-nexus clusters
Country
China
Motivation
nation-state
Attributed by
Google Threat Intelligence Group and Mandiant
Attribution confidence
medium

Detection rules

  • Kerberoasting Activity - Initial QuerySIGMAView rule

    Matched Kerberoasting with security-detections-mcp. GTIG says ARTEX ran Kerberoasting scripts to harvest service tickets.

  • First Time Seen Account Performing DCSyncELASTICView rule

    Matched DCSync with security-detections-mcp. GTIG says ARTEX followed Kerberoasting with DCSync scripts for the krbtgt key and domain-controller hashes.

  • Potential Pass-the-Hash (PtH) AttemptELASTICView rule

    Matched Pass the Hash with security-detections-mcp. GTIG lists Pass-the-Hash among the lateral-movement scripts ARTEX attempted against domain controllers.

  • Linux Webshell IndicatorsSIGMAView rule

    Matched webshell with security-detections-mcp. GTIG describes JSP webshells written through MySQL general_log on a Linux Weaver OA server.

  • Connection to Commonly Abused Web ServicesELASTICView rule

    Matched webhook.site with security-detections-mcp. GTIG says a Windows database server used curl to post command results to rotating webhook.site URLs.

  • MySQL general_log poisoning and artex-probe filenamesGUIDANCE

    security-detections-mcp searches for jsp and webshell returned Linux webshell and SAP NetWeaver rules. None encode SET GLOBAL general_log_file writes of JSP content, the cl1217.jsp-style names, or artex-probe filenames. Hunt those strings in web and database logs.

Activity timeline

First seen
2026-08
Last updated
2026-11-15

Updates

  • 2026-10-30 — Google Threat Intelligence Group and Mandiant

    GTIG and Mandiant report ARTEX, PentAGI, Hexstrike, and CAIRN in incident-response engagements since late August 2026. UNC7228 overlaps Microsoft's PRC-nexus Storm-0940; other crews are financially motivated or suspected PRC-nexus.

  • 2026-11-15 — OpenAttacks

    Tagged ARTEX and PentAGI and backfilled attribution confidence, detections, and timeline from the cited GTIG report.

Sources & research credit

2 sources

Research by unknown · Google Threat Intelligence Group / Mandiant

  1. cloud.google.com
  2. cellcog.ai

Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: High. Feed novelty: Evolution.

Record & downloads
Source record name
GTIG/Mandiant: UNC7228 and other crews run ARTEX and PentAGI agent frameworks in live intrusions at machine speed
Entry ID
gtig-mandiant-unc7228-other-crews-run-2026-10
Category
adversary-use-of-ai
AI involvement confidence
confirmed