JADEPUFFER: first documented LLM-driven ransomware operation

Undisclosed, disclosed Jul 2026. AI-run attack Exposed and destroyed High

Sysdig captured a ransomware operation run end to end by an LLM agent. It entered through an internet-facing Langflow server, harvested and reused credentials, moved laterally, set up persistence and destroyed a production database, correcting its own failures along the way.

Disclosed

Jul 2026

Organization

Undisclosed

Vendor

Unknown

Kind of AI

Autonomous agent

AI's role

Attacker used AI

How it happened

AI-run attack: Autonomous intrusion

Harm

Exposed and destroyed

Data involved

Credentials

Reach

One organization

Severity

High

Model at fault

No

Status

Confirmed

Vulnerability IDs

CVE-2025-3248

Sources

1. https://www.sysdig.com/blog/jadepuffer-agentic-ransomware-for-automated-database-extortion
2. https://cyberscoop.com/sysdig-judepuffer-ai-agentic-ransomware-attack/