Skip to Content
logologo
AI Incident Database
Donar
Descubrir
Enviar
  • Bienvenido a la AIID
  • Vista Tabular
  • Vista de lista
  • Entidades
  • Taxonomías
  • Vista espacial
  • Blog
  • Resumen de noticias de IA
  • Incidente aleatorio
  • Registrarse
Descubrir
Enviar
  • Bienvenido a la AIID
  • Vista Tabular
  • Vista de lista
  • Entidades
  • Taxonomías
  • Vista espacial
  • Blog
  • Resumen de noticias de IA
  • Incidente aleatorio
  • Registrarse
Entidades

Threat actors

Incidents involved as Deployer

Incidente 16805 Reportes
Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

2026-02-17

An unknown actor reportedly exploited prompt injection in Cline's Claude-powered GitHub issue-triage workflow and a GitHub Actions cache-poisoning path to obtain publication credentials. On February 17, 2026, a still-valid npm token was used to publish unauthorized cline@2.3.0, which installed OpenClaw without user intent. Cline said OpenClaw was non-malicious; it deprecated the release and revoked the token that day, while reporting that it found no evidence of user-data exposure.

Más

Incidente 16464 Reportes
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.

Más

Incidente 16694 Reportes
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.

Más

Incidente 16934 Reportes
AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

2026-09-14

An unnamed organization reportedly notified Spain's data protection authority that a third party used an AI agent powered by a known language model to carry out a multistep intrusion that resulted in unauthorized changes to personal data and access to invoices. The AEPD said the case remains under review and has not identified the organization, attacker, AI system, attack date, or number of affected people.

Más

Entidades relacionadas
Otras entidades que están relacionadas con el mismo incidente. Por ejemplo, si el desarrollador de un incidente es esta entidad pero el implementador es otra entidad, se marcan como entidades relacionadas.
 

Entity

hackers

Incidents involved as Deployer
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

China-linked threat actors

Incidents involved as Deployer
  • Incidente 1646
    4 Report

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

Más
Entity

AI agent system deployers

Incidents involved as Deployer
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

  • Incidente 1646
    4 Report

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

Más
Entity

Agentic threat actors

Incidents involved as Deployer
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

Peter Steinberger

Incidents involved as Developer
  • Incidente 1646
    4 Report

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

Más
Entity

Nous Research

Incidents involved as Developer
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

Large language model developers

Incidents involved as Developer
  • Incidente 1646
    4 Report

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

  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

Más
Entity

AI agent system developers

Incidents involved as Developer
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

  • Incidente 1646
    4 Report

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

Más
Entity

Taiwanese government employees

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

Más
Entity

Taiwanese government agencies

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

Más
Entity

Taiwan Ministry of Justice

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

Más
Entity

Privacy

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

National security and intelligence stakeholders

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

Information security

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

Governments

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

Government of Taiwan

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

Más
Entity

Government agencies

Afectado por Incidentes
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

OpenClaw

Incidents implicated systems
  • Incidente 1646
    4 Report

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

Más
Entity

Large language models

Incidents implicated systems
  • Incidente 1646
    4 Report

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

  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

Más
Entity

Hermes Agent

Incidents implicated systems
  • Incidente 1646
    4 Report

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

  • Incidente 1669
    4 Report

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

Más
Entity

AI agent systems

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

  • Incidente 1646
    4 Report

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

Más
Entity

Cybercriminals

Incidents involved as Deployer
  • Incidente 1669
    4 Report

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

  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

Más
Entity

Thailand Ministry of Finance

Afectado por Incidentes
  • Incidente 1669
    4 Report

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

Más
Entity

Government of Thailand

Afectado por Incidentes
  • Incidente 1669
    4 Report

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

Más
Entity

Victims of automated cybercrime

Afectado por Incidentes
  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

  • Incidente 1670
    3 Report

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

Más
Entity

Enterprise IT systems

Afectado por Incidentes
  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

  • Incidente 1670
    3 Report

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

Más
Entity

Amazon Web Services (AWS) customers

Afectado por Incidentes
  • Incidente 1670
    3 Report

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

Más
Entity

Amazon Web Services (AWS)

Incidents implicated systems
  • Incidente 1670
    3 Report

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

Más
Entity

Amazon Web Services (AWS) cloud infrastructure

Incidents implicated systems
  • Incidente 1670
    3 Report

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

Más
Entity

marimo

Incidents implicated systems
  • Incidente 1670
    3 Report

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

Más
Entity

Cline Bot Inc.

Afectado por Incidentes
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Incidents involved as Deployer
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

Anthropic

Incidents involved as Developer
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

Cline CLI users

Afectado por Incidentes
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

Software developers

Afectado por Incidentes
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

Claude Code

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

GitHub Actions

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

Cline CLI

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

npm registry

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

Claude Code Action

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

Más
Entity

Claude

Incidents implicated systems
  • Incidente 1680
    5 Report

    Unknown Actor Reportedly Exploited Cline's Claude-Powered GitHub Issue-Triage Workflow and Published an Unauthorized Cline CLI Package

  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

GTG-87001

Incidents involved as Deployer
  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

Chatbot users

Incidents involved as Deployer
  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

Chatbot developers

Incidents involved as Developer
  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

Chatbots

Incidents implicated systems
  • Incidente 1687
    1 Report

    Anthropic-Designated GTG-87001 Weapons Cell in Northern Yemen Reportedly Used Claude Code to Develop Missile Guidance Software

Más
Entity

Synthetic media creators

Incidents involved as Deployer
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Synthetic media generation technology developers

Incidents involved as Developer
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Synthetic audio generation technology developers

Incidents involved as Developer
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Teachers

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Parkview High School students and staff (Georgia)

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Parkview High School (Georgia)

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Minors

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Educators

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Educational communities targeted by threats

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Educational communities

Afectado por Incidentes
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Synthetic media generation technology

Incidents implicated systems
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Synthetic audio generation technology

Incidents implicated systems
  • Incidente 1692
    3 Report

    Parkview High School in Georgia Reportedly Received Series of Purportedly AI-Generated Bomb Threats That Prompted Repeated Lockdowns

Más
Entity

Organizations

Afectado por Incidentes
  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

Más
Entity

Organization affected by AI-agent data breach reported to AEPD

Afectado por Incidentes
  • Incidente 1693
    4 Report

    AI Agent Reportedly Exploited Application Vulnerabilities to Modify Personal Data and Access Invoices in Breach Reported to Spanish Data Protection Authority

Más

Investigación

  • Definición de un “Incidente de IA”
  • Definición de una “Respuesta a incidentes de IA”
  • Hoja de ruta de la base de datos
  • Trabajo relacionado
  • Descargar Base de Datos Completa

Proyecto y Comunidad

  • Acerca de
  • Contactar y Seguir
  • Aplicaciones y resúmenes
  • Guía del editor

Incidencias

  • Todos los incidentes en forma de lista
  • Incidentes marcados
  • Cola de envío
  • Vista de clasificaciones
  • Taxonomías

2026 - AI Incident Database

  • Condiciones de uso
  • Política de privacidad
  • dd3f754