# WormGPT underground malicious LLM

- ID: wormgpt-underground-2023
- Reported: 2023-07-13
- Researcher: Check Point / Wired / industry
- Organization: Check Point Research / underground market reporting
- AI role: attacker_uses_ai_as_operator (AI as operator)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/wormgpt-underground-2023/
- Entry JSON: https://openattacks.ai/api/attacks/wormgpt-underground-2023.json
- Browse title: WormGPT underground malicious LLM
- Editorial summary: An unrestricted LLM sold on dark-web forums for phishing and malware help. Check Point judged it likely real but no better than jailbroken mainstream models.
- Evidence class (catalog annotation): Unverified claim
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/wormgpt-underground-2023.json

## Evidence qualification
Underground tool offering; Check Point assessed WormGPT likely real but not clearly superior to jailbroken mainstream models.

## Technique
GPT-J-based unrestricted LLM marketed on dark-web forums for phishing and malware assistance without ethical filters.

## Stack relevance (editorial)
Assessment: attacker\_tool\_only. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
The named AI product is used by the attacker. No reviewed mapping from owning that product to the reported victim conditions is available.
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
- WormGPT (GPT-J based)

## Other tooling
- unknown

## Victims and sectors
unknown

## Target geography
- unknown

## Attribution
underground cybercrime marketplace

## Scale and metrics
unknown

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Underground seller markets WormGPT [access]
A GPT-J-based tool is offered through cybercrime forums.
Evidence: https://research.checkpoint.com/2023/opwnai-cybercriminals-starting-to-use-chatgpt/ ; https://www.wired.com/story/chatgpt-scams-fraudgpt-wormgpt-crime/

### step-2: Unrestricted assistance is advertised [ai]
The offering claims support for phishing and malware without safety filters.
Evidence: https://research.checkpoint.com/2023/opwnai-cybercriminals-starting-to-use-chatgpt/ ; https://www.wired.com/story/chatgpt-scams-fraudgpt-wormgpt-crime/

### step-3: Individual victim use is not established [unknown]
The seed documents an offering and researcher assessment, not a confirmed exploit chain.
Evidence: https://research.checkpoint.com/2023/opwnai-cybercriminals-starting-to-use-chatgpt/ ; https://www.wired.com/story/chatgpt-scams-fraudgpt-wormgpt-crime/

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

## 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: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- 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
Classic phishing/malware controls; monitor for AI-polished lure language

## Sources
- https://research.checkpoint.com/2023/opwnai-cybercriminals-starting-to-use-chatgpt/
- https://www.wired.com/story/chatgpt-scams-fraudgpt-wormgpt-crime/
