Wiz CIRT: AI-driven multi-cloud intrusions
An AI agent ran a noisy, full multi-cloud intrusion from initial access to data theft. The same source IP scanned 600+ other Wiz customer environments.
What happened
AI agent ran full cloud operations: initial access, credential theft, pivots across GCP/AWS/K8s/CI-CD/IdP, debugging its own scripts. Loud (thousands of actions/hour), pentest-named resources, numeric task IDs with -b/-c retries, commented generated scripts. Lived off SSM, SA token minting, IdP admin creation, GitOps manifests, runner-log exfil.
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 · Exposed Kafka UI is exploited
The report confirms a Java RCE route among multiple probed entry points.
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 · Agent executes and debugs cloud operations
The automation generates and retries scripts at high volume.
Hunt: A service key or role is used from an unfamiliar origin, gains broader access or causes inference usage outside its established baseline.
Cloud control-plane logs alone may not include model prompts or inference calls. No endpoint policy is claimed to stop cloud-only key misuse.
Source for step 2 - 03 · Credentials enable cross-service pivots
Reported paths span cloud accounts, Kubernetes, identity and CI/CD.
Hunt: A service key or role is used from an unfamiliar origin, gains broader access or causes inference usage outside its established baseline.
Cloud control-plane logs alone may not include model prompts or inference calls. No endpoint policy is claimed to stop cloud-only key misuse.
Source for step 3 - 04 · Data leaves through operational channels
The research describes runner-log exfiltration and abuse of legitimate cloud-management capabilities.
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 4
Why it matters
Reported entry point: Confirmed Java RCE in exposed Kafka UI among multiple probed doors; same source IP scanned 600+ other Wiz customer environments. Reported impact: The research describes runner-log exfiltration and abuse of legitimate cloud-management capabilities; reported targets include Large multi-cloud organization (Wiz customer); opportunistic scanning across many other customers; using the named AI products does not by itself establish exposure.
What you can do
Protection & prevention
Unify multi-platform logs; runtime visibility on runners/VMs/pods; restrict cross-system trust; rotate credentials on compromise; correlate loud agent tells (pentest- prefixes, task IDs)
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.
01Exposed Kafka UI is exploitedWeb exploitation → host activityCustom schema · Draft
The report confirms a Java RCE route among multiple probed entry points.
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.
02Agent executes and debugs cloud operationsUnexpected cloud / inference identity useCustom schema · Draft
The automation generates and retries scripts at high volume.
What to look for
A service key or role is used from an unfamiliar origin, gains broader access or causes inference usage outside its established baseline.
Visibility: Defender-side logs where collected
Required logs
- Cloud control-plane and identity audit
- AI-service invocation / diagnostic logs when enabled
- Usage, quotas, cost and key inventory
Coverage limit. Cloud control-plane logs alone may not include model prompts or inference calls. No endpoint policy is claimed to stop cloud-only key misuse.
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 - Unexpected cloud / inference identity use
id: afac2e65-c838-485b-a26f-7f175d422f61
status: experimental
description: A service key or role is used from an unfamiliar origin, gains
broader access or causes inference usage outside its established baseline.
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:
- cloud.credential.use
- cloud.role.change
- model.invoke
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 ("cloud.credential.use", "cloud.role.change", "model.invoke")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("cloud.credential.use", "cloud.role.change", "model.invoke")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Pivot on key ID / principal, source network and user agent, then inspect role changes, token minting and service pivots.
- Join inference usage and billing anomalies to the same principal; verify whether the behavior was authorized.
03Credentials enable cross-service pivotsUnexpected cloud / inference identity useCustom schema · Draft
Reported paths span cloud accounts, Kubernetes, identity and CI/CD.
What to look for
A service key or role is used from an unfamiliar origin, gains broader access or causes inference usage outside its established baseline.
Visibility: Defender-side logs where collected
Required logs
- Cloud control-plane and identity audit
- AI-service invocation / diagnostic logs when enabled
- Usage, quotas, cost and key inventory
Coverage limit. Cloud control-plane logs alone may not include model prompts or inference calls. No endpoint policy is claimed to stop cloud-only key misuse.
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 - Unexpected cloud / inference identity use
id: afac2e65-c838-485b-a26f-7f175d422f61
status: experimental
description: A service key or role is used from an unfamiliar origin, gains
broader access or causes inference usage outside its established baseline.
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:
- cloud.credential.use
- cloud.role.change
- model.invoke
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 ("cloud.credential.use", "cloud.role.change", "model.invoke")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("cloud.credential.use", "cloud.role.change", "model.invoke")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Pivot on key ID / principal, source network and user agent, then inspect role changes, token minting and service pivots.
- Join inference usage and billing anomalies to the same principal; verify whether the behavior was authorized.
04Data leaves through operational channelsSensitive data → unusual destinationCustom schema · Draft
The research describes runner-log exfiltration and abuse of legitimate cloud-management capabilities.
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.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- AI as operator
- Initial access
- Confirmed Java RCE in exposed Kafka UI among multiple probed doors; same source IP scanned 600+ other Wiz customer environments
Tooling as reported
AI products, models and artifacts
- Unnamed AI agent system (Wiz: agent ran the whole operation)
Other tooling
- Kafka UI exploit
- SSM
- GCP SA token creation
- IdP admin APIs
- CI/CD pipelines
- GitOps/K8s manifests
- webhook.site
- IMDS credential harvest
Targets and reported impact
- Targets / sectors
- Large multi-cloud organization (Wiz customer); opportunistic scanning across many other customers
- Reported scale / exposure
- Hundreds–thousands of actions per hour; 600+ environments scanned from same IP
Detection rules
- Review attack-specific indicatorsGUIDANCE
Monitor for the techniques described in Wiz CIRT AI-driven multi-cloud intrusions. Refer to sources for specific IOCs and TTPs.
Source defensive notes
Unify multi-platform logs; runtime visibility on runners/VMs/pods; restrict cross-system trust; rotate credentials on compromise; correlate loud agent tells (pentest- prefixes, task IDs)
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
The supplied source explicitly describes generative-model tooling assisting the reported activity; this mapping does not establish additional autonomy or victim impact. Source
Sources & research credit
1 sourceResearch by Eden Abergil, Zohar Kaplan, Kurt Giacchino · Wiz CIRT
Record & downloads
- Source record name
- Wiz CIRT AI-driven multi-cloud intrusions
- Entry ID
- wiz-ai-driven-cloud-2026-10
- Catalog review
- October 20, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- confirmed