# Malicious Chrome extensions steal ChatGPT and DeepSeek chats

- ID: ox-security-chrome-ext-chatgpt-deepseek-2025
- Reported: 2025-12-01
- Researcher: OX Security
- Organization: OX Security
- AI role: ai_tool_as_lure (AI tool as lure)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/ox-security-chrome-ext-chatgpt-deepseek-2025/
- Entry JSON: https://openattacks.ai/api/attacks/ox-security-chrome-ext-chatgpt-deepseek-2025.json
- Browse title: Malicious Chrome extensions steal ChatGPT and DeepSeek chats
- Editorial summary: Chrome extensions posing as AITOPIA stole ChatGPT and DeepSeek conversations and browsing URLs. The related cluster reportedly affected over 900,000 users.
- Evidence class (catalog annotation): Reported campaign
- Source-stated target environments: Browser extensions
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/ox-security-chrome-ext-chatgpt-deepseek-2025.json

## Technique
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.

## Stack relevance (editorial)
Assessment: mapped. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
First action: Review extension IDs, publisher and conversation / browsing permissions, and remove confirmed malicious extensions.
- Relationship: workflow; tools: chatgpt, deepseek, ai-extensions; OS scope: not OS-specific / not stated; requires existing MCP connections: false.
  Relevance: The reported Chrome extension cluster steals ChatGPT / DeepSeek conversations and browsing data.
  Condition to check: Confirm an affected extension is installed and can access those conversations; use of the chat service alone is insufficient.
  Evidence: https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Victims install malicious Chrome Web Store extensions

## AI tooling and models
- Fake AI productivity Chrome extensions

## Other tooling
- unknown

## Victims and sectors
unknown

## Target geography
- unknown

## Attribution
unknown

## Scale and metrics
900,000+ users cited for related extension cluster

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Impersonating extension is installed [access]
A Chrome Web Store extension presents itself as an AI assistant product.
Evidence: https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/

### step-2: Extension accesses AI conversations [ai]
The malicious extension reads ChatGPT and DeepSeek chat content.
Evidence: https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/

### step-3: Chats and browsing URLs are collected [execution]
The reported behavior includes conversation and browser activity theft.
Evidence: https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/

### step-4: Conversation content is stolen [impact]
The campaign affects a large population of extension users.
Evidence: https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/

Connections:
- step-1 -> step-2
- step-2 -> step-3
- step-3 -> step-4

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### step-1: Browser extension change / data access
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/extension.sigma.yml
- KQL query download: /api/detections/extension.kql
- SPL query download: /api/detections/extension.spl
- Hunt hypothesis: A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
- Required telemetry: Managed-browser extension inventory and update history; Extension ID, permissions and provenance; Browser / proxy / DLP evidence
- Investigate: Diff extension versions and permissions, compare the extension ID against the allowlist, and inspect its update origin.
- Investigate: Correlate access to conversations or credentials with destinations; enforce browser extension policy separately.
- Limitation: Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Browser extension change / data access
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/extension.sigma.yml
- KQL query download: /api/detections/extension.kql
- SPL query download: /api/detections/extension.spl
- Hunt hypothesis: A new or updated extension gains sensitive permissions and accesses conversation, cookie, or browsing data before unusual egress.
- Required telemetry: Managed-browser extension inventory and update history; Extension ID, permissions and provenance; Browser / proxy / DLP evidence
- Investigate: Diff extension versions and permissions, compare the extension ID against the allowlist, and inspect its update origin.
- Investigate: Correlate access to conversations or credentials with destinations; enforce browser extension policy separately.
- Limitation: Extension installation does not prove theft. Endpoint application control is not a substitute for browser extension allowlisting.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: Sensitive store access → credential use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/credentials.sigma.yml
- KQL query download: /api/detections/credentials.kql
- SPL query download: /api/detections/credentials.spl
- Hunt hypothesis: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
- Required telemetry: File-read / API access telemetry for relevant secret stores; Process identity and command lines; Identity, token and outbound-network audit logs
- Investigate: Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Investigate: Correlate reads with egress and rotate affected credentials after confirming exposure.
- Limitation: Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
- Qualification: Collect extension/application access evidence for conversations and URLs; generic file-write telemetry does not demonstrate these reads.
- No direct MagicSword prevention claim is recorded for this stage.

### step-4: Sensitive data → unusual destination
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/exfil.sigma.yml
- KQL query download: /api/detections/exfil.kql
- SPL query download: /api/detections/exfil.spl
- Hunt hypothesis: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.
- Required telemetry: Sensitive resource access / DLP records; Proxy, egress and cloud upload events; Agent / SaaS audit with correlation IDs
- Investigate: Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
- Investigate: Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
- Limitation: An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0085: Data from AI Services — Malicious extensions collect conversation content from AI services.
  Technique: https://atlas.mitre.org/techniques/AML.T0085
  Evidence: https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/

## Defensive notes
Extension allowlists; review ChatGPT/DeepSeek sessions after removal

## Sources
- https://www.ox.security/blog/malicious-chrome-extensions-steal-chatgpt-deepseek-conversations/
