Sysdig reveals JadePuffer: first fully LLM-driven agentic ransomware campaign
By
Phil Muncaster
Summary
Sysdig's Threat Research Team has identified JadePuffer, what they claim is the first fully agentic ransomware campaign driven entirely by a large language model (LLM). The campaign exploited CVE-2025-3248 in an internet-facing Langflow instance to execute an automated, adaptive attack resulting in a destructive database-extortion playbook against a production database server. Unlike traditional human-driven toolkits, the attack capabilities were delivered by an autonomous AI agent, marking a significant evolution in cyber threats.
Source
bskySysdig reveals JadePuffer: first fully LLM-driven agentic ransomware campaigninfosecurity-magazine.comKey quotes
· 3 pulledCloud security firm Sysdig has released details on what it claims to be the world's first ransomware campaign completely driven by a large language model (LLM).
Dubbed JadePuffer, the campaign targeted an internet-facing Langflow instance by exploiting CVE-2025-3248.
Attack capabilities were delivered by an agent rather than a human-driven toolkit, the Sysdig research claimed.
You might also wanna read
JadePuffer: The First Complete LLM-Driven Ransomware Attack
AI Agent Exploits Langflow RCE to Automate Database Ransomware Attack
JadePuffer ransomware used AI agent to automate entire attack
JadePuffer ransomware used AI agent to automate entire attack
AI Agent Executes 'First' End-To-End Ransomware Attack
Security Analysis: AI Agent Frameworks' Code Execution Vulnerabilities and WASM Sandbox Solution
The article discusses security vulnerabilities in popular AI agent frameworks like LangChain, AutoGen, and SWE-Agent that execute LLM-genera
github.com·5mo ago
Security Risks of Large Language Models and Coding Agents Revealed at Black Hat
The article discusses the security risks associated with the increasing use of Large Language Models (LLMs) and coding agents, highlighting
garymarcus.substack.com·10mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.