AI Incident Database #1578 · 2026-07-01
LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database
Sysdig reported that a ransomware operator it dubbed JADEPUFFER used an LLM-driven agent to turn access through a vulnerable internet-facing Langflow deployment into a database-extortion operation.
- Risk class (MIT)
- Not yet classified
- Reports
- 4
- Developers and deployers named
- 6
Reports
- JADEPUFFER: 6 Things to Know About the First AI-Driven Ransomware Operation · cybelangel.com, 2026-07-07
- JadePuffer: The First Complete LLM-Driven Ransomware Attack · darkreading.com, 2026-07-06
- Researchers Claim First Fully Agentic Ransomware: JadePuffer · infosecurity-magazine.com, 2026-07-06
- JADEPUFFER: Agentic ransomware for automated database extortion · sysdig.com, 2026-07-01
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.