Skip to content

Back to the record

Jul 1, 2026Confirmed

Sysdig reports LLM-driven ransomware agent JADEPUFFER hit a production database via exposed Langflow

Rogue: Caused harmAI loose in the worldData lossDERIVED

Approved by person, Oct 11, 2026. How entries are approved

Showing full summaries.

Sysdig reported that a ransomware operator it calls JADEPUFFER used an LLM-driven agent to turn access through a vulnerable internet-facing Langflow deployment into database extortion. The activity reached a production database server, allegedly leaving the environment damaged and unrecoverable, with a ransom demand.

What this means for youCriminals are now using AI agents to run attacks that once needed skilled people. If you run AI tools or workflow software, check that none are reachable from the open internet, keep them updated, and keep backups stored offline.

Sources

Data from the AI Incident Database (incidentdatabase.ai), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. IAAI-21.

Source data license: CC BY-SA 4.0 (database). Report contents keep their own rights; reports.text, submissions, images and videos are excluded from the data license.

rogue:R4

Covered by snapshot 45

da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a

This entry is record number 2169. It has not been edited since it was approved; the hash above would not match if it had. How to verify

Sysdig reports LLM-driven ransomware agent JADEPUFFER hit a production database via exposed Langflow | Vigilo AI Watch