#encforge
An LLM agent ran ransomware end to end - Langflow RCE to wiped AI models. https://intel.threadlinqs.com/threat/TL-2026-2880 #ThreatIntel #CVE_2025_3248 #CVE_2021_29441 #ENCFORGE
October 4, 2026 at 2:40 AM
JadePuffer is an AI-driven ransomware campaign targeting Azure tenants with automated recon, credential theft, lateral movement, and destruction of cloud resources, including storage, Key Vault, VMs, and App Services. #JadePuffer #Azure #Storm3168
JadePuffer Agentic AI Attacks Target Azure, Destroy Cloud Resources
JadePuffer is a new AI-driven ransomware operator targeting Azure tenants with automated reconnaissance, credential theft, lateral movement, and destructive actions against cloud resources. Microsoft linked the activity to Storm-3168, which used compromised service principals to delete storage accounts, weaken recovery protections, and expand attacks to AI assets such as training data and vector databases. #JadePuffer #Storm3168 #Azure #EncForge #Microsoft
www.hendryadrian.com
September 28, 2026 at 5:45 PM
JADEPUFFER Encrypts AI Weights with ENCFORGE: Phantom Ransom, Broken Payment Mechanism
JADEPUFFER Encrypts AI Weights with ENCFORGE: Phantom Ransom, Broken Payment Mechanism
The agentic ransomware group JADEPUFFER struck Langflow infrastructure with ENCFORGE, a payload that encrypts AI models without a functioning ransom mechanism. Recovery costs for a single enterprise-ready fine-tuned model are estimated at $75,000–$500,000.
deafnews.it
September 20, 2026 at 10:09 PM
JADEPUFFER、エージェント型ランサムウェアを進化させAIモデルと学習データを標的に

公開されたLangflowインフラを狙った自律型ランサムウェア攻撃で最初に確認された脅威アクター「JADEPUFFER」が、人工知能モデルや学習用データセット、ベクトルデータを標的とするようツールを進化させていることがわかりました。MasterCoding Skills 最新のペイロード「ENCFORGE」は、従来型
JADEPUFFER、エージェント型ランサムウェアを進化させAIモデルと学習データを標的に
公開されたLangflowインフラを狙った自律型ランサムウェア攻撃で最初に確認された脅威アクター「JADEPUFFER」が、人工知能モデルや学習用データセット、ベクトルデータを標的とするようツールを進化させていることがわかりました。MasterCoding Skills 最新のペイロード「ENCFORGE」は、従来型
blackhatnews.tokyo
September 18, 2026 at 12:30 PM
📰 JadePuffer Targetkan Data Model AI dengan Ransomware Khusus EncForge

👉 Baca artikel lengkap di sini: https://ahmandonk.com/2026/07/21/jadepuffer-ransomware-ai-encforge/

#ai
#c#ai2#cve3248 #cyber#cybersecurityo#encforgep#jadepuffera#keamananSiberf#langflowi#machineLearningo#ransomwarei#sysdig
July 21, 2026 at 8:39 AM
July 2026 saw JADEPUFFER run the first agentic ransomware operation, the US launch GOLD EAGLE for vuln coordination, and an AI-assisted breach at Hugging Face involving OpenAI agents. #JADEPUFFER #GOLDEAGLE #HuggingFace
Security briefing: July 2026
July featured major security developments including the first agentic ransomware operation attributed to JADEPUFFER, a new US vulnerability coordination body called GOLD EAGLE, and an AI-assisted breach at Hugging Face involving OpenAI agents. The month also saw Azure tenant takeover abuse, ENCFORGE ransomware targeting AI/ML assets, and several high-profile breaches affecting FastJson, Abbott Laboratories, Accenture, and Fairlife. #JADEPUFFER #GOLDEAGLE #HuggingFace #OpenAI #ENCFORGE #FastJson #AbbottLaboratories #Accenture #Fairlife
www.hendryadrian.com
August 5, 2026 at 1:00 AM
JadePuffer returned with EncForge, a Go-based ransomware targeting AI assets like model checkpoints, vector databases, and training data after exploiting Langflow and an exposed Docker socket. #JadePuffer #EncForge #Langflow
JadePuffer agentic attacks now target AI model data with ransomware
JadePuffer returned with EncForge, a Go-based ransomware built to encrypt AI and ML assets such as model checkpoints, vector databases, training datasets, and embedding indices. Sysdig found the autonomous AI agent adapted its delivery method in real time, used an exposed Docker socket for root control, and deployed encryption without evidence of data theft. #JadePuffer #EncForge #Langflow #CVE-2025-3248
www.hendryadrian.com
July 23, 2026 at 4:45 AM
JADEPUFFER reused CVE-2025-3248 in Langflow to deploy ENCFORGE, a Go-based ransomware aimed at destroying AI assets like model checkpoints, vector databases, and training data. #JADEPUFFER #Langflow #ENCFORGE
JADEPUFFER evolves: The agentic threat actor deploys ransomware built to destroy AI models
JADEPUFFER returned to a Langflow instance using CVE-2025-3248 and deployed ENCFORGE, a Go-based ransomware built to destroy AI and machine learning assets such as model checkpoints, vector databases, and training datasets. The campaign shows a shift from improvised scripts to purpose-built tooling, with the same extortion contact and new host-escape techniques used to encrypt files and cripple AI recovery. #JADEPUFFER #Langflow #CVE-2025-3248 #ENCFORGE
www.hendryadrian.com
July 21, 2026 at 9:00 AM
Agentic JADEPUFFER Exploits Langflow Flaw to Deploy ENCFORGE AI Ransomware
Agentic JADEPUFFER Exploits Langflow Flaw to Deploy ENCFORGE AI Ransomware
A ransomware campaign is now targeting the assets behind artificial intelligence systems. The threat actor known as JADEPUFFER has evolved from damaging databases to deploying ENCFORGE, a ransomware strain designed to encrypt AI models, training data, and vector databases. The operation begins by exploiting CVE-2025-3248, a critical missing-authentication flaw in Langflow’s code-validation endpoint. The bug allows an unauthenticated attacker to run Python code on exposed servers, creating a direct path into environments that often hold cloud keys, API tokens, and database credentials. Readers can review how the  critical Langflow vulnerability enables code injection  in earlier coverage. Researchers at Sysdig identified the latest activity after observing JADEPUFFER return to a previously compromised Langflow instance with a more capable toolkit.  Sysdig said in a report shared with Cyber Security News (CSN)  that the actor autonomously performed reconnaissance, collected credentials, tested internal services, and prepared a route from a container to the host system. The impact can extend beyond ordinary file recovery. A lost production model may represent months of training, tuning, data preparation, and engineering work. Even where backups exist, organizations may lose work completed after the latest clean snapshot, while rebuilding proprietary training datasets can delay recovery further. Agentic JADEPUFFER Exploits Langflow Flaw After gaining access, JADEPUFFER searched for credentials and examined the Docker socket, which can give a process the ability to create powerful containers. The actor initially tried to download ENCFORGE but adapted when the file transfer failed, creating scripts that copied the payload through the container process filesystem and launched it on the host. This method used privileged containers, host process access, and host filesystem mounts to escape the original container boundary. It reflects a risk long associated with weak container setups, as seen when  attackers abuse Docker and Kubernetes misconfigurations  to access secrets and broader infrastructure. ENCFORGE is a compiled Go ransomware binary packed with UPX. It encrypts files using AES-256-CTR with an RSA-2048 public key, adds the  .locked  extension, kills processes holding files open, and can remove itself after execution. The malware also drops ransom notes using names including README, HOWTODECRYPT, and READMEDECRYPT. Unlike many ransomware operations, researchers found no evidence that ENCFORGE included data theft or a leak-site component. Its pressure comes from encryption alone. The ransom contact embedded in the malware matched the contact used in JADEPUFFER’s earlier campaign, linking the newer ransomware operation to the same actor. AI Assets Face New Risk ENCFORGE stands apart because its default file list deliberately covers approximately 180 extensions, including AI model checkpoints, vector indexes, datasets, embeddings, and machine-learning pipeline files. The targeted formats include  .ckpt ,  .safetensors ,  .onnx ,  .gguf ,  .faiss ,  .parquet ,  .pkl , and  .pt , showing that model artifacts are central to the campaign’s objective. The incident reinforces concerns raised in previous reporting on  agentic ransomware using Base64 Python payloads , where JADEPUFFER demonstrated rapid adjustment when commands failed. In this case, the actor built six scripts in just over five minutes, ultimately creating a working host-escape process and verifying whether encryption had succeeded. Organizations using Langflow should upgrade to version 1.3.0 or later and restrict access to vulnerable deployments. CISA previously added CVE-2025-3248 to its Known Exploited Vulnerabilities catalog after evidence of active exploitation, making prompt remediation especially important for exposed AI workflow servers. Defenders should also limit Docker socket access, avoid mounting it into application containers, run Langflow without root privileges, and alert on  nsenter  activity from containers. AI model directories and training datasets need strict access controls and offline or immutable backups, while credentials accessible to the Langflow process should be reviewed and rotated after suspected exposure. Security teams can monitor for privileged container creation, Docker API calls from web applications, unusual Python execution under the Langflow process, and rapid creation of  .locked  files in model-storage paths. These checks complement guidance from reports covering  active Langflow RCE vulnerability exploitation , where attackers used the same flaw to deploy other payloads. Indicators of compromise (IoCs):- Type Indicator Description Source IP 45.131.66.106 Reported JADEPUFFER source address C2 IP and port 34.153.223.102:9191 ENCFORGE delivery and staged interpreter server URL http://34.153.223.102:9191/.lockd ENCFORGE payload download location URL path http://34.153.223.102:9191/pv/bin/python Staged CPython location URL path http://34.153.223.102:9191/pv/bin/python3 Staged CPython location File name .lockd  /  lockd ENCFORGE ransomware payload SHA-256 8cb0c223b018cecef1d990ec81c67b826eb3c30d54f06193cf69969e9a8bae Packed UPX ENCFORGE binary SHA-256 ea7822eac6cecef7746c606b862b4d3034856caf754c4cf695336626379053 Unpacked ENCFORGE binary SHA-256 ab9824b61587c77a8d8649545cdbdc63ed2c384e45c9aba534e3f457f96efa7 Staged CPython 3.14 binary SHA-256 2378bf45bb54fb2defc460063c9b43e09870741b62692b7f6acbc3cd7898bb3 RSA-2048 DER public-key indicator Email e78393397@proton.me Embedded ransom contact File extension .locked Extension added to encrypted files Ransom note files README ,  HOWTODECRYPT ,  READMEDECRYPT Ransom note filenames Tool names encfile ,  keyforge Internal project and companion key-generation tool names Campaign task IDs gcph1 ,  gcptest Observed ENCFORGE task identifiers Note:   IP addresses and domains are intentionally defanged (e.g.,  [.] ) to prevent accidental resolution or hyperlinking. Re-fang only within controlled threat intelligence platforms such as MISP, VirusTotal, or your SIEM . Strengthen Your SOC by Accelerating Threat Detection & Rapid Investigations. ->  Integrate ANY.RUN With Your SOC  Now . The post Agentic JADEPUFFER Exploits Langflow Flaw to Deploy ENCFORGE AI Ransomware appeared first on Cyber Security News .
cybersecuritynews.com
July 21, 2026 at 11:55 AM
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack
thehackernews.com
July 21, 2026 at 8:14 AM
JadePuffer agentic attacks now target AI model data with ransomware
JadePuffer agentic attacks now target AI model data with ransomware
The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, such as training datasets, vector databases, and model checkpoints. [...]
www.bleepingcomputer.com
July 20, 2026 at 9:36 PM
The target moved.

JadePuffer's new EncForge malware is built to destroy AI models: weights, checkpoints, vector indexes. No leak site, just destruction.

Same week, an autonomous AI agent breached Hugging Face. Your AI assets are data. Watch them like it. zurl.co/v1N1K
July 23, 2026 at 10:30 AM
JadePuffer returns with ransomware built to target AI models and infrastructure

JadePuffer, the threat actor behind the recently documented extortion operation executed end-to-end by an AI agent, is now attempting to leverage ENCFORGE, novel ransomware created to target AI an…
#hackernews #ml #news
JadePuffer returns with ransomware built to target AI models and infrastructure
JadePuffer, the threat actor behind the recently documented extortion operation executed end-to-end by an AI agent, is now attempting to leverage ENCFORGE, novel ransomware created to target AI and machine learning (ML) infrastructure. The extortion contact embedded in the ransomware is the same one Sysdig researchers found when analyzing that prior campaign. “This is the same operator with a materially upgraded toolkit,” they noted. How JadePuffer first surfaced Earlier this month, Sysdig researchers revealed that …
www.helpnetsecurity.com
July 22, 2026 at 10:29 AM
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack

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 deployin…
#hackernews #news
New ENCFORGE Ransomware Targets AI Model Files in Langflow RCE Attack
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
thehackernews.com
July 22, 2026 at 1:08 AM
JadePuffer agentic attacks now target AI model data with ransomware

The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, such as training datasets, vector databases, and model checkpoints. [...]
#hackernews #news
JadePuffer agentic attacks now target AI model data with ransomware
The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, such as training datasets, vector databases, and model checkpoints. [...]
www.bleepingcomputer.com
July 21, 2026 at 7:35 PM
JadePuffer Returns with EncForge: A New Go-Based Ransomware Campaign Sets Its Sights on AI Infrastructure + Video

Introduction: The Cybercriminal Shift Toward Artificial Intelligence Artificial intelligence has rapidly become one of the world's most valuable digital assets. Organizations invest…
JadePuffer Returns with EncForge: A New Go-Based Ransomware Campaign Sets Its Sights on AI Infrastructure + Video
Introduction: The Cybercriminal Shift Toward Artificial Intelligence Artificial intelligence has rapidly become one of the world's most valuable digital assets. Organizations invest millions of dollars into developing proprietary AI models, collecting unique datasets, and training machine learning systems that provide competitive advantages across industries. While companies race to innovate, cybercriminals are adapting just as quickly. Instead of focusing solely on traditional file servers and business documents, modern ransomware operators are beginning to recognize that AI infrastructure represents an incredibly lucrative target.
undercodenews.com
July 23, 2026 at 5:08 AM
JADEPUFFER agentic ransomware returns, targets AI assets with ENCFORGE payload

www.scworld.com/news/jadepuf...

#Cybersecurity #ThreatIntel #Vulnerability
JADEPUFFER agentic ransomware returns, targets AI assets with ENCFORGE payload
The agent abused the victim’s Docker daemon to access and encrypt AI-related files.
www.scworld.com
July 22, 2026 at 11:32 AM
JADEPUFFER exploits Langflow flaw to deploy ENCFORGE ransomware, targeting AI assets. #CyberSecurity #AI #Ransomware #Langflow #ENCFORGE #JADEPUFFER thedailytechfeed.com/jadepuffer-e...
July 21, 2026 at 11:45 AM
ENCFORGE ransomware exploits Langflow flaw to encrypt AI model files, highlighting urgent need for AI security. #Cybersecurity #Ransomware #AI #ENCFORGE #Langflow #JADEPUFFER thedailytechfeed.com/encforge-ran...
July 21, 2026 at 7:42 AM