Malicious Chrome extensions steal ChatGPT and DeepSeek chats
Chrome extensions posing as AITOPIA stole ChatGPT and DeepSeek conversations and browsing URLs. The related cluster reportedly affected over 900,000 users.
What happened
AITOPIA-impersonating Chrome extensions stole ChatGPT and DeepSeek conversation content plus browsing URLs. Reported impact over 900,000 users for related malicious AI-themed extensions in the campaign cluster.
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 · Impersonating extension is installed
A Chrome Web Store extension presents itself as an AI assistant product.
Hunt: A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
Source for step 1 - 02 · Extension accesses AI conversations
The malicious extension reads ChatGPT and DeepSeek chat content.
Hunt: A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
Source for step 2 - 03 · Chats and browsing URLs are collected
The reported behavior includes conversation and browser activity theft.
Hunt: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
Source for step 3 - 04 · Conversation content is stolen
The campaign affects a large population of extension users.
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: Victims install malicious Chrome Web Store extensions. Reported impact: The campaign affects a large population of extension users.
Check these source-linked conditions against your setup.
The reported Chrome extension cluster steals ChatGPT / DeepSeek conversations and browsing data.
Conditions to check- Confirm an affected extension is installed and can access those conversations; use of the chat service alone is insufficient.
Source-linked applicability guidance. Confirm current scope in the original report.
What you can do
Protection & prevention
Review extension IDs, publisher and conversation / browsing permissions, and remove confirmed malicious extensions.
Extension allowlists; review ChatGPT/DeepSeek sessions after removal
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.
01Impersonating extension is installedBrowser extension change / data accessCustom schema · Draft
A Chrome Web Store extension presents itself as an AI assistant product.
What to look for
A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
Visibility: Defender-side logs where collected
Required logs
- Managed-browser extension inventory and update history
- Extension ID, permissions and provenance
- Browser / proxy / DLP evidence
Coverage limit. Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
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 - Browser extension change / data access
id: 0dd8a9d2-e0c8-4768-a49d-5fc2f09a6d7c
status: experimental
description: A new or updated extension gains sensitive permissions and accesses
conversation, cookie, or browsing data before unusual egress.
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:
- browser.extension.install
- browser.extension.update
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 ("browser.extension.install", "browser.extension.update")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("browser.extension.install", "browser.extension.update")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Diff extension versions and permissions, compare the extension ID against the allowlist, and inspect its update origin.
- Correlate access to conversations or credentials with destinations; enforce browser extension policy separately.
02Extension accesses AI conversationsBrowser extension change / data accessCustom schema · Draft
The malicious extension reads ChatGPT and DeepSeek chat content.
What to look for
A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
Visibility: Defender-side logs where collected
Required logs
- Managed-browser extension inventory and update history
- Extension ID, permissions and provenance
- Browser / proxy / DLP evidence
Coverage limit. Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
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 - Browser extension change / data access
id: 0dd8a9d2-e0c8-4768-a49d-5fc2f09a6d7c
status: experimental
description: A new or updated extension gains sensitive permissions and accesses
conversation, cookie, or browsing data before unusual egress.
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:
- browser.extension.install
- browser.extension.update
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 ("browser.extension.install", "browser.extension.update")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("browser.extension.install", "browser.extension.update")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Diff extension versions and permissions, compare the extension ID against the allowlist, and inspect its update origin.
- Correlate access to conversations or credentials with destinations; enforce browser extension policy separately.
03Chats and browsing URLs are collectedSensitive store access → credential useCustom schema · Draft
The reported behavior includes conversation and browser activity theft.
What to look for
An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
Collect extension/application access evidence for conversations and URLs; generic file-write telemetry does not demonstrate these reads.
Visibility: Defender-side logs where collected
Required logs
- File-read / API access telemetry for relevant secret stores
- Process identity and command lines
- Identity, token and outbound-network audit logs
Coverage limit. Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
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 store access → credential use
id: 46c46c62-2d83-4198-a8bf-d6637094527b
status: experimental
description: An unexpected process or tool accesses credential stores and is
followed by token use or outbound transfer inconsistent with the owner.
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:
- secret.read
- credential.store.read
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 ("secret.read", "credential.store.read")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("secret.read", "credential.store.read")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Correlate reads with egress and rotate affected credentials after confirming exposure.
04Conversation content is stolenSensitive data → unusual destinationCustom schema · Draft
The campaign affects a large population of extension users.
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 tool as lure
- Initial access
- Victims install malicious Chrome Web Store extensions
Tooling as reported
AI products, models and artifacts
- Fake AI productivity Chrome extensions
Targets and reported impact
- Reported scale / exposure
- 900,000+ users cited for related extension cluster
Detection rules
- Review attack-specific indicatorsGUIDANCE
Monitor for the techniques described in Malicious Chrome extensions steal ChatGPT and DeepSeek chats. Refer to sources for specific IOCs and TTPs.
Source defensive notes
Extension allowlists; review ChatGPT/DeepSeek sessions after removal
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Malicious extensions collect conversation content from AI services. Source
Sources & research credit
1 sourceResearch by OX Security · OX Security
Record & downloads
- Source record name
- Malicious Chrome extensions steal ChatGPT and DeepSeek chats
- Entry ID
- ox-security-chrome-ext-chatgpt-deepseek-2025
- Catalog review
- October 20, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- confirmed