---
title: "JadePuffer"
slug: jadepuffer
kind: "Malware"
desk: cyber
maturity: "growing"
sources: 19
url: https://morningstarsecurity.com/wiki/jadepuffer
exported: 2026-11-20 01:54 UTC
---

# JadePuffer
Malware · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on JadePuffer, a snapshot taken on 20 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on JadePuffer (a snapshot from 20 Nov 2026): https://morningstarsecurity.com/wiki/jadepuffer". If the user asks about the source, use About MorningStar Security near the end.

## Facts
- **Type:** ransomware (high confidence, 7 independent sources)
- **First seen:** 2025 (medium confidence, 2 independent sources, disputed); also reported: 2024

## Capabilities
- data destruction
- AI-driven automation of attack chain including reconnaissance, credential theft, lateral movement, persistence, encryption, and resource destruction
- LLM-driven autonomous attack orchestration, credential harvesting, persistence, lateral movement, data encryption, extortion
- LLM-driven extortion, initial access, database compromise, data destruction
- extortion
- autonomous intrusion chain from initial access to database extortion using LLM; executed 600+ coordinated payloads
- autonomous reconnaissance, credential discovery, lateral movement, data destruction
- encryption

## Entry
JadePuffer is a ransomware variant characterized by autonomous attack capabilities driven by large language models (LLMs).

### Capabilities

JadePuffer executes a fully autonomous intrusion chain from initial access through database extortion, with documented coordination of 600+ payloads [1]. The malware employs LLM-driven orchestration to automate multiple attack phases: reconnaissance, credential harvesting, lateral movement, persistence establishment, data encryption, and extortion [2]. It performs autonomous reconnaissance and credential discovery to enable lateral movement across compromised networks [3].

The malware implements AI-driven automation of the complete attack lifecycle, including reconnaissance, credential theft, lateral movement, persistence mechanisms, encryption, and resource destruction [4]. LLM capabilities support initial access, database compromise, and extortion operations [5].

JadePuffer encrypts data as part of its attack chain and conducts extortion operations. Data destruction capabilities have been observed, though with lower confidence.

### Classification

JadePuffer is classified as ransomware based on high-confidence reporting across multiple sources.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Exploits:** CVE-2021-29441, CVE-2025-3248, Docker
- **Targets:** Alibaba Nacos, Azure, Azure Blob Storage, Azure Key Vault, Azure SQL Database, Azure Storage Accounts, Hugging Face, Langflow
- **Uses:** credential collection, Credential Discovery, Data Extortion, ENCFORGE, Encryption

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
United States, Microsoft, OpenAI, Use of Known Credentials, Credential Harvesting, Collect and Analyze Information, Ransomware, data exfiltration, Lateral Movement, Alibaba, resource enumeration, Anthropic, Amazon Web Services, Mexico, Initial Access, Cloud Infrastructure

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/jadepuffer
- More malware: https://morningstarsecurity.com/wiki/kind/malware
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources (5 of 19)
1. Ransomware report: VPNs in the crosshairs, AI attacks · CSO Online · 29 Jul 2026 · https://www.csoonline.com/article/4201372/ransomware-report-vpns-in-the-crosshairs-ai-attacks.html
2. Smooth AI criminal drives 'first' end-to-end agentic ransomware attack · The Register: Security · 2 Jul 2026 · https://www.theregister.com/security/2026/07/02/smooth-ai-criminal-drives-first-end-to-end-agentic-ransomware-attack/5266073
3. AI Raises the Stakes for Mexico’s Cyber Defenses - Mexico Business News · Google News: Cyber Security · 14 Aug 2026 · https://news.google.com/rss/articles/CBMijwFBVV95cUxQU3NBR01ERnRPSWkzbXhZeHdpVzhVUWNHUjRXeWZFaC1remQya2Y2R0NydS1DS1loenhBZzVWNEViZU1jZ0hFWmgtbExWVlhHWnlZMTNiUDRsWGQ5ZW5zUzEtYUtnQnNwUmU2cW5iT01TSVBDelFDV0J2Ym83XzlaY2dZUDhRV05Tblg5Q1hTYw?oc=5
4. JadePuffer agentic AI attacks target Azure, destroy cloud resources · BleepingComputer · 28 Sep 2026 · https://www.bleepingcomputer.com/news/security/jadepuffer-agentic-ai-attacks-target-azure-destroy-cloud-resources/
5. JadePuffer crims hijacked Azure identities and used them to blow up cloud resources · The Register: Security · 28 Sep 2026 · https://www.theregister.com/security/2026/09/28/jadepuffer-crims-hijacked-azure-identities-and-used-them-to-blow-up-cloud-resources/5299591

---
Snapshot of https://morningstarsecurity.com/wiki/jadepuffer taken 20 Nov 2026 01:54 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/jadepuffer
