Not classified

Dragos: intruder used Claude and GPT to find and password-spray a Mexican water utility's OT gateway

An unidentified intruder in Mexican government networks used commercial LLMs as its main operator, and the AI itself flagged and attacked an industrial gateway at a municipal water utility.

What happened

An unidentified intruder in Mexican government networks used commercial LLMs as its main operator, and the AI itself flagged and attacked an industrial gateway at a municipal water utility.

Read the original sourceAdditional source: labs.cloudsecurityalliance.org

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

    An unidentified intruder in Mexican government networks used commercial LLMs as its main operator, and the AI itself flagged and attacked an industrial gateway at a municipal water utility.

    Source for step 2
  3. 03 · AI involvement

    Anthropic Claude (primary technical executor), OpenAI GPT models (data analysis and reporting)

    Source for step 3

Why it matters

Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Government; Critical infrastructure; 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
Additional role
LLM-generated malware

Tooling as reported

AI products, models and artifacts

  • Anthropic Claude (primary technical executor), OpenAI GPT models (data analysis and reporting)

Targets and reported impact

Targets / sectors
Government; Critical infrastructure

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

Reported attribution

Unnamed (Spanish-language operator; tracked by Dragos as TAT26-12 per secondary reporting)

Sources & research credit

2 sources

Research by unknown · Dragos

  1. dragos.com
  2. labs.cloudsecurityalliance.org

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
Dragos: intruder used Claude and GPT to find and password-spray a Mexican water utility's OT gateway
Entry ID
dragos-intruder-used-claude-gpt-find-2026-05
Category
adversary-use-of-ai
AI involvement confidence
confirmed