# Fake DeepSeek / Grok Windows clients deliver stealers and backdoors

- ID: deepseek-grok-fake-windows-clients-2025
- Reported: 2025-02-01
- Researcher: Kaspersky / Securelist; McAfee; Unit 42
- Organization: Kaspersky
- 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/deepseek-grok-fake-windows-clients-2025/
- Entry JSON: https://openattacks.ai/api/attacks/deepseek-grok-fake-windows-clients-2025.json
- Browse title: Fake DeepSeek and Grok Windows clients deliver stealers and backdoors
- Editorial summary: Fake DeepSeek and Grok desktop installers delivered stealers, SSH backdoors, Vidar, the BrowserVenom traffic proxy and Gh0stRAT variants.
- Evidence class (catalog annotation): Reported campaign
- Source-stated target environments: Windows
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/deepseek-grok-fake-windows-clients-2025.json

## Technique
No official DeepSeek Windows desktop client; fake DeepSeek/Grok installers delivered Python stealers, SSH backdoors, Vidar, BrowserVenom (browser traffic proxying), and Chinese-language trojanized installers including Gh0stRAT variants.

## Stack relevance (editorial)
Assessment: mapped. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
First action: Verify desktop installer provenance and investigate unapproved executables and persistence.
- Relationship: lure; tools: deepseek, grok; OS scope: windows; requires existing MCP connections: false.
  Relevance: Fake DeepSeek / Grok Windows installers deliver the payloads in this account.
  Condition to check: The reported path requires installation of a malicious desktop package.
  Evidence: https://securelist.com/backdoors-and-stealers-prey-on-deepseek-and-grok/115801/ ; https://www.kaspersky.com/blog/trojans-disguised-as-deepseek-grok-clients/53116/ ; https://www.mcafee.com/blogs/other-blogs/mcafee-labs/bogus-deepseek-ai-installers-are-infecting-devices-with-malware-research-finds/
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Users download fake AI desktop clients from unofficial sites/ads

## AI tooling and models
- Fake [DeepSeek](https://github.com/deepseek-ai) / [Grok](https://x.ai/grok) branded installers

## Other tooling
- Vidar
- BrowserVenom
- Gh0stRAT
- [Python](https://github.com/python/cpython) stealers

## Victims and sectors
Users seeking DeepSeek/Grok desktop apps

## Target geography
- Multiple regions
The source describes global distribution. Chinese-language installers do not establish victims in China.

## Attribution
unknown

## Scale and metrics
unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: User finds an unofficial AI client [access]
Fake DeepSeek or Grok desktop downloads are promoted through sites and ads.
Evidence: https://securelist.com/backdoors-and-stealers-prey-on-deepseek-and-grok/115801/ ; https://www.kaspersky.com/blog/trojans-disguised-as-deepseek-grok-clients/53116/ ; https://www.mcafee.com/blogs/other-blogs/mcafee-labs/bogus-deepseek-ai-installers-are-infecting-devices-with-malware-research-finds/

### step-2: AI product branding is impersonated [ai]
The installer presents itself as a trusted model client.
Evidence: https://securelist.com/backdoors-and-stealers-prey-on-deepseek-and-grok/115801/ ; https://www.kaspersky.com/blog/trojans-disguised-as-deepseek-grok-clients/53116/ ; https://www.mcafee.com/blogs/other-blogs/mcafee-labs/bogus-deepseek-ai-installers-are-infecting-devices-with-malware-research-finds/

### step-3: Trojanized installer runs [execution]
Reported branches deliver stealers, SSH backdoors or RAT variants.
Evidence: https://securelist.com/backdoors-and-stealers-prey-on-deepseek-and-grok/115801/ ; https://www.kaspersky.com/blog/trojans-disguised-as-deepseek-grok-clients/53116/ ; https://www.mcafee.com/blogs/other-blogs/mcafee-labs/bogus-deepseek-ai-installers-are-infecting-devices-with-malware-research-finds/

### step-4: Data theft or remote access [impact]
Payloads steal browser data, proxy traffic or establish attacker access.
Evidence: https://securelist.com/backdoors-and-stealers-prey-on-deepseek-and-grok/115801/ ; https://www.kaspersky.com/blog/trojans-disguised-as-deepseek-grok-clients/53116/ ; https://www.mcafee.com/blogs/other-blogs/mcafee-labs/bogus-deepseek-ai-installers-are-infecting-devices-with-malware-research-finds/

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: Lure → user action / delivery
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/phishing.sigma.yml
- KQL query download: /api/detections/phishing.kql
- SPL query download: /api/detections/phishing.spl
- Hunt hypothesis: An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
- Required telemetry: Email / secure-web-gateway records; Browser redirects, downloads and URL reputation; User reports and downstream execution / identity events
- Investigate: Reconstruct redirect and delivery provenance using original report indicators, without visiting payload URLs.
- Investigate: Correlate the click with the actual download, consent or execution; verify the sender through an independent channel.
- Limitation: Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
- Qualification: Trace the advertisement and unofficial download to file provenance and later execution.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Lure → user action / delivery
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/phishing.sigma.yml
- KQL query download: /api/detections/phishing.kql
- SPL query download: /api/detections/phishing.spl
- Hunt hypothesis: An impersonating message, ad or website leads to a suspicious download, consent request, pasted command or payment instruction.
- Required telemetry: Email / secure-web-gateway records; Browser redirects, downloads and URL reputation; User reports and downstream execution / identity events
- Investigate: Reconstruct redirect and delivery provenance using original report indicators, without visiting payload URLs.
- Investigate: Correlate the click with the actual download, consent or execution; verify the sender through an independent channel.
- Limitation: Polished text, AI branding and a novel domain do not prove maliciousness or AI generation. Follow-on evidence matters.
- Qualification: Use download provenance and follow-on behavior; an AI product name is not sufficient evidence of a malicious installer.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: Unapproved Windows program execution
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: native
- SIGMA query download: /api/detections/windows-install.sigma.yml
- KQL query download: /api/detections/windows-install.kql
- SPL query download: /api/detections/windows-install.spl
- Hunt hypothesis: A newly downloaded or staged executable runs from a user-writable location and exhibits the reported follow-on behavior.
- Required telemetry: Windows process creation; Download provenance and file hashes; File certificate information and application-control audit / block events
- Investigate: Verify publisher, hash, origin, prevalence and local approval rather than trusting a product name or signature.
- Investigate: Trace child processes and related credential, network or persistence events.
- Limitation: Many approved installers run from user-writable folders. These events are hunt candidates, not proof of malware or an enforced block.
- Conditional MagicSword policy: Use MagicSword to audit the actual executable's signer, publisher or hash, then enforce a policy that denies unapproved code on managed Windows hosts.
- Policy scope: The reported Windows installers and payloads on managed devices; validate signer and hash policy coverage.
- Policy limitation: Policy opportunity, not tested incident coverage. Requires enrolled Windows devices, a policy covering the actual executable, and enforcement. Audit mode records decisions without blocking; allowed tools and in-process / cloud actions can remain reachable.
- Policy reference: https://www.magicsword.io/use-cases/application-control?utm_source=openattacks&utm_medium=referral&utm_content=stage-control

### step-4: 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.
- 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.
No source-backed mapping is currently recorded.

## Defensive notes
Only official web apps; block unsigned AI installers; MagicSword prevent unexpected stealers

## Sources
- https://securelist.com/backdoors-and-stealers-prey-on-deepseek-and-grok/115801/
- https://www.kaspersky.com/blog/trojans-disguised-as-deepseek-grok-clients/53116/
- https://www.mcafee.com/blogs/other-blogs/mcafee-labs/bogus-deepseek-ai-installers-are-infecting-devices-with-malware-research-finds/
