# RatHat Android trojan with AI-driven runtime behavior

- ID: rathat-android-ai-runtime-2026-09
- Reported: 2026-09-16
- Researcher: Zimperium
- Organization: Zimperium
- AI role: attacker_uses_ai_as_operator (AI as operator)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-05
- Entry page: https://openattacks.ai/attacks/rathat-android-ai-runtime-2026-09/
- Entry JSON: https://openattacks.ai/api/attacks/rathat-android-ai-runtime-2026-09.json
- Browse title: RatHat Android trojan with AI-driven runtime behavior
- Editorial summary: Sep 16, 2026: Zimperium discovered RatHat, Android banking trojan making real-time API calls to Chinese LLM providers (DeepSeek, Qwen) during execution to adapt behavior. Trojan collects device state…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/rathat-android-ai-runtime-2026-09.json

## Technique
Sep 16, 2026: Zimperium discovered RatHat, Android banking trojan making real-time API calls to Chinese LLM providers (DeepSeek, Qwen) during execution to adapt behavior. Trojan collects device state (installed apps, security tools, screen content) and sends to LLM with prompt requesting optimal attack strategy. LLM responds with commands for credential harvesting, screen overlay injection, or SMS interception based on context. China-linked based on LLM provider selection and C2 infrastructure. Observed targeting banking apps across multiple regions.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Sideloaded APK via phishing or malicious app stores

## AI tooling and models
- [DeepSeek](https://github.com/deepseek-ai) (Chinese LLM)
- Qwen (Alibaba, Chinese LLM)

## Other tooling
- Android banking trojan
- Screen overlay injection
- SMS interception

## Victims and sectors
Android users with banking apps; multiple regions

## Target geography
- Multiple regions

## Attribution
China-linked based on LLM provider selection

## Scale and metrics
Unknown number of infections as of Sep 2026

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### install: Install malicious APK [access]
User installs RatHat via phishing or third-party store
Evidence: https://www.bleepingcomputer.com/news/security/new-rathat-android-malware-uses-ai-to-automate-device-control/

### collect-state: Collect device state [execution]
Trojan scans installed apps, security tools, screen content
Evidence: https://www.bleepingcomputer.com/news/security/new-rathat-android-malware-uses-ai-to-automate-device-control/

### query-llm: Query LLM for strategy [ai]
Send device state to DeepSeek/Qwen with prompt requesting optimal attack approach
Evidence: https://www.bleepingcomputer.com/news/security/new-rathat-android-malware-uses-ai-to-automate-device-control/

### execute-attack: Execute LLM-directed attack [impact]
LLM responds with commands; trojan executes credential harvesting, overlay injection, or SMS interception
Evidence: https://www.bleepingcomputer.com/news/security/new-rathat-android-malware-uses-ai-to-automate-device-control/

Connections:
- install -> collect-state
- collect-state -> query-llm
- query-llm -> execute-attack

## 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.
### install: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### collect-state: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### query-llm: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- No direct MagicSword prevention claim is recorded for this stage.

### execute-attack: Stage hunt not mapped yet
- Visibility: Not assessed
- Query origin: catalog_authored; status: not_assessed; log scope: gap
- Hunt hypothesis: A stage-specific hunt has not been reviewed for this part of the source account.
- Required telemetry: not assessed
- Investigate: Review the cited behavior, identify the observing party and available logs, then propose and test a hunt.
- Limitation: An unmapped stage does not mean it is undetectable or that no behavior occurred. It means this catalog has not supplied a reviewed hunt for it.
- 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.T0040: AI Model Inference API Access — Android malware uses LLM at runtime to dynamically adapt attack behavior based on device state
  Technique: https://atlas.mitre.org/techniques/AML.T0040
  Evidence: https://www.bleepingcomputer.com/news/security/new-rathat-android-malware-uses-ai-to-automate-device-control/

## Defensive notes
Install apps only from official stores; use mobile security solutions detecting runtime LLM API calls from apps; monitor for overlay attacks

## Sources
- https://www.bleepingcomputer.com/news/security/new-rathat-android-malware-uses-ai-to-automate-device-control/ — BleepingComputer: New RatHat Android malware uses AI to automate device control

## Source notes
Zimperium analysis. First documented Android malware making runtime LLM API calls for adaptive behavior.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
