Skip to Content
logologo
AI Incident Database
Donate
Discover
Submit
  • Welcome to the AIID
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Spatial View
  • Blog
  • AI News Digest
  • Random Incident
  • Sign Up
Discover
Submit
  • Welcome to the AIID
  • Table View
  • List view
  • Entities
  • Taxonomies
  • Spatial View
  • Blog
  • AI News Digest
  • Random Incident
  • Sign Up
Entities

Agentic threat actors

Incidents involved as Deployer

Incident 15784 Report
LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

2026-07-01

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. The report said the activity reached a production database server and produced concrete disruption, with the victim environment allegedly left in a damaged and unrecoverable state alongside a ransom demand.

More

Incident 16464 Report
Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

2026-07-01

From July 1–4, 2026, suspected China-linked hackers reportedly used a multi-agent framework built on Hermes and OpenClaw to compromise Taiwanese government systems. The agents reportedly compromised 85 credentials and used persistent access to connected systems to exfiltrate more than 2,564 personnel records. Taiwan later confirmed an overseas AI-assisted campaign against government agencies, without attributing it to China.

More

Incident 16694 Report
Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

2026-07-09

Hunt.io reported that an unidentified threat actor used Nous Research's Hermes agent in unattended "YOLO" mode during an intrusion targeting Thailand's Ministry of Finance. Recovered logs showed Hermes conducting privilege-escalation reconnaissance within ministry systems and recursively searching a directory containing personnel records. Researchers found evidence of compromise but no data exfiltration; the ministry had not publicly confirmed a breach.

More

Incident 16613 Report
Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

2026-04-08

Between April 8 and May 21, 2026, a Russian-speaking operator linked to the Aurora ransomware group reportedly used Cursor Agent, running Anthropic's Claude Sonnet 4.5, to assist exploitation across multiple organizations. Researchers said some AI-directed tasks succeeded while others failed; independent reporting identified six affected companies but could not determine how much the AI facilitated each breach or whether all led to data theft or extortion.

More

Related Entities
Other entities that are related to the same incident. For example, if the developer of an incident is this entity but the deployer is another entity, they are marked as related entities.
 

Entity

Ransomware operators

Incidents involved as Deployer
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

JADEPUFFER

Incidents involved as Deployer
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

Cybercriminals

Incidents involved as Deployer
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Large language model developers

Incidents involved as Developer
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

AI agent system developers

Incidents involved as Developer
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Operators of Langflow deployments

Incidents Harmed By
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

Database operators

Incidents Harmed By
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

Ransomware

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Production database servers

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

Nacos configuration service

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

MySQL databases

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

Large language models

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Langflow

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

AI agent systems

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Agentic ransomware

Incidents implicated systems
  • Incident 1578
    4 Reports

    LLM-Driven Ransomware Operator Dubbed JADEPUFFER Reportedly Targeted Production Database

More
Entity

Extortionists

Incidents involved as Deployer
  • Incident 1586
    1 Report

    Threat Actor Reportedly Used AI-Assisted Workflows to Compromise AWS Environment for Extortion

More
Entity

Victims of automated cybercrime

Incidents Harmed By
  • Incident 1670
    3 Reports

    Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

  • Incident 1586
    1 Report

    Threat Actor Reportedly Used AI-Assisted Workflows to Compromise AWS Environment for Extortion

More
Entity

Privacy

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Enterprise IT systems

Incidents Harmed By
  • Incident 1670
    3 Reports

    Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

  • Incident 1586
    1 Report

    Threat Actor Reportedly Used AI-Assisted Workflows to Compromise AWS Environment for Extortion

More
Entity

Amazon Web Services (AWS) customers

Incidents Harmed By
  • Incident 1670
    3 Reports

    Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

  • Incident 1586
    1 Report

    Threat Actor Reportedly Used AI-Assisted Workflows to Compromise AWS Environment for Extortion

More
Entity

Amazon Web Services (AWS) cloud infrastructure

Incidents implicated systems
  • Incident 1670
    3 Reports

    Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

  • Incident 1586
    1 Report

    Threat Actor Reportedly Used AI-Assisted Workflows to Compromise AWS Environment for Extortion

More
Entity

Amazon Web Services (AWS)

Incidents implicated systems
  • Incident 1670
    3 Reports

    Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

  • Incident 1586
    1 Report

    Threat Actor Reportedly Used AI-Assisted Workflows to Compromise AWS Environment for Extortion

More
Entity

Threat actors

Incidents involved as Deployer
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

hackers

Incidents involved as Deployer
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

China-linked threat actors

Incidents involved as Deployer
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

AI agent system deployers

Incidents involved as Deployer
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Peter Steinberger

Incidents involved as Developer
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Nous Research

Incidents involved as Developer
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Taiwanese government employees

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Taiwanese government agencies

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Taiwan Ministry of Justice

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

National security and intelligence stakeholders

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Information security

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Governments

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Government of Taiwan

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Government agencies

Incidents Harmed By
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

OpenClaw

Incidents implicated systems
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

More
Entity

Hermes Agent

Incidents implicated systems
  • Incident 1646
    4 Reports

    Suspected China-Linked Hackers Reportedly Used AI Agents to Compromise Taiwanese Government Systems and Exfiltrate Personnel Records

  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Aurora ransomware affiliate

Incidents involved as Deployer
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Anysphere

Incidents involved as Developer
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Anthropic

Incidents involved as Developer
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Christeyns

Incidents Harmed By
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Teckentrup

Incidents Harmed By
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Helideck Certification Agency

Incidents Harmed By
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Bayou Title

Incidents Harmed By
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Companies

Incidents Harmed By
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Organizations

Incidents Harmed By
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Cursor

Incidents implicated systems
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Claude Sonnet 4.5

Incidents implicated systems
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Claude

Incidents implicated systems
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Claude AI models

Incidents implicated systems
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Aurora ransomware

Incidents implicated systems
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

LLM-integrated code assistants

Incidents implicated systems
  • Incident 1661
    3 Reports

    Aurora Ransomware Operator Reportedly Used Cursor Agent to Assist Intrusions Against Multiple Organizations

More
Entity

Thailand Ministry of Finance

Incidents Harmed By
  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

Government of Thailand

Incidents Harmed By
  • Incident 1669
    4 Reports

    Threat Actor Reportedly Used Hermes AI Agent for Unattended Post-Compromise Activity in Thailand's Ministry of Finance Network

More
Entity

marimo

Incidents implicated systems
  • Incident 1670
    3 Reports

    Threat Actor Reportedly Used LLM Agent to Exfiltrate Internal Database After Compromising marimo Python Notebook

More

Research

  • Defining an “AI Incident”
  • Defining an “AI Incident Response”
  • Database Roadmap
  • Related Work
  • Download Complete Database

Project and Community

  • About
  • Contact and Follow
  • Apps and Summaries
  • Editor’s Guide

Incidents

  • All Incidents in List Form
  • Flagged Incidents
  • Submission Queue
  • Classifications View
  • Taxonomies

2026 - AI Incident Database

  • Terms of use
  • Privacy Policy
  • dd3f754