Cato CTRL: new WormGPT variants are jailbroken wrappers around xAI Grok and Mistral Mixtral
Underground WormGPT clones sold via Telegram were shown to be guardrail-bypassing system prompts layered on Grok's API and on a likely fine-tuned Mixtral.
What happened
Underground WormGPT clones sold via Telegram were shown to be guardrail-bypassing system prompts layered on Grok's API and on a likely fine-tuned Mixtral.
How it happened
Read the flow as text & sources
A summary diagram derived from the entry fields, not a verified detailed sequence. Unknown steps remain explicit; an edge describes the reported relationship between steps.
- 01 · Reported initial access
unknown
Source for step 1 - 02 · Reported activity
Underground WormGPT clones sold via Telegram were shown to be guardrail-bypassing system prompts layered on Grok's API and on a likely fine-tuned Mixtral.
Source for step 2 - 03 · AI involvement
xAI Grok API (keanu-WormGPT) · Mistral Mixtral (xzin0vich-WormGPT)
Source for step 3
Why it matters
Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Technology and AI companies; Multiple sectors; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.
What you can do
Protection & prevention
Prevention guidance has not been recorded for this entry. Review the original report for available mitigations.
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
- LLM-generated malware
- Additional role
- AI credential theft
Tooling as reported
AI products, models and artifacts
- xAI Grok API (keanu-WormGPT)
- Mistral Mixtral (xzin0vich-WormGPT)
Targets and reported impact
- Targets / sectors
- Technology and AI companies; Multiple sectors
Target geography was not captured by the Notion feed. Actor attribution is not used as a victim location.
Reported attribution
keanu; xzin0vich (BreachForums sellers)
Structured attribution
- Actor
- keanu; xzin0vich (BreachForums sellers)
- Motivation
- cybercrime
Sources & research credit
3 sourcesResearch by unknown · Cato Networks (Cato CTRL)
Imported from the AI Threat Watch Notion feed (an automated daily scan); not yet editorially reviewed. Feed severity: Medium. Feed novelty: Evolution.
Record & downloads
- Source record name
- Cato CTRL: new WormGPT variants are jailbroken wrappers around xAI Grok and Mistral Mixtral
- Entry ID
- cato-ctrl-new-wormgpt-variants-jailbroken-2025-06
- Category
- adversary-use-of-ai
- AI involvement confidence
- vendor-asserted