WormGPT underground malicious LLM
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.
What happened
GPT-J-based unrestricted LLM marketed on dark-web forums for phishing and malware assistance without ethical filters.
How it happened
Read the flow as text & sources
A catalog reconstruction of the supplied source account. Underground tool offering; Check Point assessed WormGPT likely real but not clearly superior to jailbroken mainstream models.
- 01 · Underground seller markets WormGPT
A GPT-J-based tool is offered through cybercrime forums.
Source for step 1 - 02 · Unrestricted assistance is advertised
The offering claims support for phishing and malware without safety filters.
Source for step 2 - 03 · Individual victim use is not established
The seed documents an offering and researcher assessment, not a confirmed exploit chain.
Source for step 3
Why it matters
Reported impact: the cited report does not establish a confirmed victim outcome; using the named AI products does not by itself establish exposure.
What you can do
Protection & prevention
Classic phishing/malware controls; monitor for AI-polished lure language
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Technical detailsTooling, impact
Attack context
- AI's role
- AI as operator
Tooling as reported
AI products, models and artifacts
- WormGPT (GPT-J based)
Reported attribution
underground cybercrime marketplace
Structured attribution
- Actor
- underground cybercrime marketplace
- Motivation
- financially-motivated
Detection rules
- Review attack-specific indicatorsGUIDANCE
Monitor for the techniques described in WormGPT underground malicious LLM. Refer to sources for specific IOCs and TTPs.
Source defensive notes
Classic phishing/malware controls; monitor for AI-polished lure language
Sources & research credit
2 sourcesResearch by Check Point / Wired / industry · Check Point Research / underground market reporting
Record & downloads
- Source record name
- WormGPT underground malicious LLM
- Entry ID
- wormgpt-underground-2023
- Catalog review
- October 20, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- unverified