# SentinelLABS uncovers MalTerminal, GPT-4-powered malware, and hunts LLM malware by embedded keys and prompts

- ID: sentinellabs-uncovers-malterminal-gpt-4-powered-2025-09
- Reported: 2025-09-19
- Researcher: unknown
- Organization: SentinelLABS
- AI role: llm_generated_malware (LLM-generated malware)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: not assessed
- Entry page: https://openattacks.ai/attacks/sentinellabs-uncovers-malterminal-gpt-4-powered-2025-09/
- Entry JSON: https://openattacks.ai/api/attacks/sentinellabs-uncovers-malterminal-gpt-4-powered-2025-09.json
- Browse title: SentinelLABS uncovers MalTerminal, GPT-4-powered malware, and hunts LLM malware by embedded keys and prompts
- Editorial summary: SentinelLABS identified possibly the earliest LLM-enabled malware and showed that embedded API keys and prompts give defenders a reliable hunting handle.
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/sentinellabs-uncovers-malterminal-gpt-4-powered-2025-09.json

## Technique
SentinelLABS identified possibly the earliest LLM-enabled malware and showed that embedded API keys and prompts give defenders a reliable hunting handle.

## 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
unknown

## AI tooling and models
- OpenAI GPT-4 chat completions API (deprecated endpoint)
- [Hugging Face](https://huggingface.co/) keys in LameHug

## Other tooling
- unknown

## Victims and sectors
Multiple sectors

## Target geography
- unknown
Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.

## Attribution
Unknown author of MalTerminal

## Scale and metrics
unknown

## Attack flow
Summary diagram derived from entry fields; a detailed sequence has not been supplied.
### entry: Reported initial access [unknown]
unknown
Evidence: https://www.sentinelone.com/labs/prompts-as-code-embedded-keys-the-hunt-for-llm-enabled-malware/ ; https://thehackernews.com/2025/09/researchers-uncover-gpt-4-powered.html ; https://securityaffairs.com/182433/malware/researchers-expose-malterminal-an-llm-enabled-malware-pioneer.html

### activity: Reported activity [execution]
SentinelLABS identified possibly the earliest LLM-enabled malware and showed that embedded API keys and prompts give defenders a reliable hunting handle.
Evidence: https://www.sentinelone.com/labs/prompts-as-code-embedded-keys-the-hunt-for-llm-enabled-malware/ ; https://thehackernews.com/2025/09/researchers-uncover-gpt-4-powered.html ; https://securityaffairs.com/182433/malware/researchers-expose-malterminal-an-llm-enabled-malware-pioneer.html

### ai: AI involvement [ai]
OpenAI GPT-4 chat completions API (deprecated endpoint) · Hugging Face keys in LameHug
Evidence: https://www.sentinelone.com/labs/prompts-as-code-embedded-keys-the-hunt-for-llm-enabled-malware/ ; https://thehackernews.com/2025/09/researchers-uncover-gpt-4-powered.html ; https://securityaffairs.com/182433/malware/researchers-expose-malterminal-an-llm-enabled-malware-pioneer.html

Connections:
- entry -> activity
- ai -> activity (AI context)

## 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.
### entry: 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.

### activity: 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.

### ai: 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.
No source-backed mapping is currently recorded.

## Defensive notes
unknown

## Sources
- https://www.sentinelone.com/labs/prompts-as-code-embedded-keys-the-hunt-for-llm-enabled-malware/
- https://thehackernews.com/2025/09/researchers-uncover-gpt-4-powered.html
- https://securityaffairs.com/182433/malware/researchers-expose-malterminal-an-llm-enabled-malware-pioneer.html

## Source notes
Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: Medium. Feed novelty: New TTP.
