Return to Threats

New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack

thehackernews.com 2026-07-21 AI agent abuse Critical

Executive Summary

Sysdig linked a second attack on the same Langflow server to JADEPUFFER, which deployed ENCFORGE, Go ransomware built to encrypt model weights, vector indexes, training datasets and other AI files.

What Happened

Researchers at Sysdig have linked a second attack on the same Langflow server to JADEPUFFER, the AI-agent-driven operator it first documented earlier this month. The same operator has now been spotted deploying ENCFORGE, a new compiled Go ransomware designed to encrypt model weights, vector indexes, training datasets, and other AI infrastructure files across the host filesystem. The entry

Affected Products

  • Langflow

Vulnerability / Attack Technique

Ransomware targeting AI model and data files

Technical Mechanism

After the Langflow RCE, the operator deployed ransomware that searches the filesystem for AI artifacts and encrypts them.

AI Security Category

AI-assisted attack

Part of the AI-Assisted Attacks topic.

Relevant Frameworks

LLM03:2025 Supply ChainMITRE ATLAS: Impact

RealGround Analysis

Ransomware now targets model weights and vector stores specifically. RealGround analysis: back up AI artifacts like any critical data.

Recommended Controls

  • Back up model weights, vector indexes and datasets offline
  • Patch and isolate Langflow

Related RealGround Service

Secure AI Agent Build · or start with the free AI Agent Security Scanner.

Sources

thehackernews.com: https://thehackernews.com/2026/07/new-encforge-ransomware-targets-ai.html

Summary and analysis written by RealGround from the source above; last updated 2026-10-18.

Talk to AI CISO