GTG-2002 'vibe hacking' data extortion via Claude Code
A criminal operator used Claude Code for reconnaissance, intrusion and data theft, then to help set ransom amounts and prepare extortion messages.
What happened
Cybercriminal GTG-2002 used Claude Code as active operator for scaled data extortion ('vibe hacking'): recon, credential harvest, network penetration, exfil, then ransom notes threatening data exposure (not classic encryptor). Actor stored preferred TTPs in CLAUDE.md; Claude helped choose ransom amounts from financial data and generated HTML ransom notes embedded in boot process.
How it happened
Read the flow as text & sources
A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.
- 01 · Internet-facing systems are scanned
Some operations also start with compromised VPN access.
Hunt: Repeated exploit or upload requests are followed by an unexpected server process, file, or outbound connection.
A scan or high request rate alone does not prove compromise or AI use. Host telemetry is needed to confirm execution.
Source for step 1 - 02 · Claude Code assists active intrusion
The actor stores preferences in CLAUDE.md and uses model help for reconnaissance and credential collection.
Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.
Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.
Source for step 2 - 03 · Data is collected and exfiltrated
The campaign penetrates networks and retrieves information.
Hunt: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
Source for step 3 - 04 · Victims receive extortion demands
Model assistance supports ransom valuation and HTML demands threatening data exposure.
Hunt: An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
Source for step 4
Why it matters
Reported entry point: Opportunistic via OSINT and scanning of Internet-facing devices; some ops began from compromised VPNs for internal access (vs later GTG-1002). Reported impact: Model assistance supports ransom valuation and HTML demands threatening data exposure; reported targets include At least 17 organizations in ~1 month: government, healthcare, emergency services, religious institutions; using the named AI products does not by itself establish exposure.
What you can do
Protection & prevention
EDR + app control on coding-agent spawned shells; hunt boot-process HTML ransom artifacts; restrict agent network egress
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Detection queries
Draft query starters grouped by the attack stages where they apply.
Start with the logs you collect. Each hunt identifies its required visibility, field mapping and limits. Queries are catalog-authored drafts using reusable behavior profiles; test with known activity and your normal baseline before alerting.
01Internet-facing systems are scannedWeb exploitation → host activityCustom schema · Draft
Some operations also start with compromised VPN access.
What to look for
Repeated exploit or upload requests are followed by an unexpected server process, file, or outbound connection.
Visibility: Defender-side logs where collected
Required logs
- Reverse-proxy / WAF request logs
- Server process and file events
- Outbound DNS / proxy records
Coverage limit. A scan or high request rate alone does not prove compromise or AI use. Host telemetry is needed to confirm execution.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Web exploitation → host activity
id: 04d900b5-0c04-46f2-a13a-91f5574fae98
status: experimental
description: Repeated exploit or upload requests are followed by an unexpected
server process, file, or outbound connection.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- web.exploit_candidate
- web.upload
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("web.exploit_candidate", "web.upload")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("web.exploit_candidate", "web.upload")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Join requests to the affected host and process tree by time and request ID.
- Inspect uploaded files and server-spawned shells; distinguish authorized testing from exploitation.
02Claude Code assists active intrusionProvider-side abuse investigationCustom schema · Draft
The actor stores preferences in CLAUDE.md and uses model help for reconnaissance and credential collection.
What to look for
A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.
Visibility: Provider / operator records
Required logs
- Provider-owned account / request audit
- Abuse-review findings and linked-account context
- Lawfully available exposed operator-session evidence
Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
repeated offensive requests and shared infrastructure or exposed operator
sessions.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- model.request
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
- For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
03Data is collected and exfiltratedSensitive data → unusual destinationCustom schema · Draft
The campaign penetrates networks and retrieves information.
What to look for
Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
Visibility: Defender-side logs where collected
Required logs
- Sensitive resource access / DLP records
- Proxy, egress and cloud upload events
- Agent / SaaS audit with correlation IDs
Coverage limit. An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Sensitive data → unusual destination
id: 04b60968-3179-4b1f-ae13-6f57c2446077
status: experimental
description: Sensitive reads are followed by outbound transfer, a public
artifact, or a tool call to a destination outside the approved workflow.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- data.export
- agent.external.send
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("data.export", "agent.external.send")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("data.export", "agent.external.send")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
04Victims receive extortion demandsLure → user action / deliveryCustom schema · Draft
Model assistance supports ransom valuation and HTML demands threatening data exposure.
What to look for
An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
Investigate extortion communications alongside the preceding data-access evidence; message polish does not prove AI involvement.
Visibility: Defender-side logs where collected
Required logs
- Email / secure-web-gateway records
- Browser redirects, downloads and URL reputation
- User reports and downstream execution / identity events
Coverage limit. Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.
Sigma
title: Hunt - Lure → user action / delivery
id: e0056b49-9905-485b-ac12-2aa076a7bc82
status: experimental
description: An impersonating message, ad or website leads to a suspicious
download, consent request, pasted command or payment instruction.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
- Authorized activity matching this broad hunt; baseline and investigate
before alerting.
level: low
logsource:
category: application
product: openattacks_audit
definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
Target and CorrelationId from the required source logs first.
detection:
selection:
EventType:
- message.link.click
- web.download
condition: selection
KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("message.link.click", "web.download")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("message.link.click", "web.download")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Reconstruct redirect and delivery provenance using original report indicators, without visiting payload URLs.
- Correlate the click with the actual download, consent or execution; verify the sender through an independent channel.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- AI as operator
- Initial access
- Opportunistic via OSINT and scanning of Internet-facing devices; some ops began from compromised VPNs for internal access (vs later GTG-1002)
Tooling as reported
AI products, models and artifacts
- Claude Code
- CLAUDE.md TTP guide
Targets and reported impact
- Targets / sectors
- At least 17 organizations in ~1 month: government, healthcare, emergency services, religious institutions
- Reported scale / exposure
- ≥17 orgs; occasional ransom demands exceeding $500,000
- Target geography
- Multiple regions
Multiple target countries are reported, but specific country names are largely redacted.
Reported attribution
GTG-2002; financially motivated cybercriminal
Structured attribution
- Actor
- GTG-2002
- Motivation
- financially-motivated
Detection rules
- Review attack-specific indicatorsGUIDANCE
Monitor for the techniques described in GTG-2002 vibe hacking data extortion via Claude Code. Refer to sources for specific IOCs and TTPs.
Source defensive notes
EDR + app control on coding-agent spawned shells; hunt boot-process HTML ransom artifacts; restrict agent network egress
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Claude Code is used as part of the extortion workflow. Source
The model supports command-driven intrusion tasks. Source
Sources & research credit
1 sourceResearch by Anthropic Threat Intelligence · Anthropic
Record & downloads
- Source record name
- GTG-2002 vibe hacking data extortion via Claude Code
- Entry ID
- gtg-2002-vibe-hacking-extortion-2025-08
- Catalog review
- October 20, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- confirmed