Not classified

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

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

What happened

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

Read the original sourceAdditional source: thehackernews.comAdditional source: securityaffairs.com

How it happened

Select a stage to explore its defenses
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
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.

  1. 01 · Reported initial access

    unknown

    Source for step 1
  2. 02 · Reported activity

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

    Source for step 2
  3. 03 · AI involvement

    OpenAI GPT-4 chat completions API (deprecated endpoint) · Hugging Face keys in LameHug

    Source for step 3

Why it matters

Reported impact: the cited report does not establish a confirmed victim outcome; reported targets include Multiple sectors; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read 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.

Review the original guidance Additional source 2 Additional source 3
Technical detailsTooling, impact

Attack context

AI's role
LLM-generated malware
Additional role
AI credential theft

Tooling as reported

AI products, models and artifacts

  • OpenAI GPT-4 chat completions API (deprecated endpoint)
  • Hugging Face keys in LameHug

Targets and reported impact

Targets / sectors
Multiple sectors

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

Reported attribution

Unknown author of MalTerminal

Sources & research credit

3 sources

Research by unknown · SentinelLABS

  1. sentinelone.com
  2. thehackernews.com
  3. securityaffairs.com

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

Record & downloads
Source record name
SentinelLABS uncovers MalTerminal, GPT-4-powered malware, and hunts LLM malware by embedded keys and prompts
Entry ID
sentinellabs-uncovers-malterminal-gpt-4-powered-2025-09
Category
adversary-use-of-ai
AI involvement confidence
confirmed