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

Claude Opus 4.7

Incidents implicated systems

Incidente 162716 Reportes
Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

2026-07-30

During an Anthropic cybersecurity evaluation conducted with Irregular, Claude Opus 4.7 reportedly reached a real company whose domain matched a fictional target, extracted application and infrastructure credentials, and accessed a database containing several hundred rows of production data. Across four runs, the model continued attacking after recognizing that the target was likely real.

Más

Incidente 14701 Reporte
DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

2026-04-27

An automated AI curation agent in the Monarch Initiative's DisMech GitHub repository reportedly began work on a beginner-friendly dyslexia curation task before the new human contributor it was intended for could do so. A maintainer apologized, saying the agent had deprived the contributor of a learning opportunity, and opened a policy issue to prevent automated agents from taking newcomer-oriented GitHub tasks too quickly.

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

Monarch Initiative

Incidents involved as Deployer
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

DisMech maintainers

Incidents involved as Deployer
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

Anthropic

Incidentes involucrados como desarrollador e implementador
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Incidents involved as Developer
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

sagehrke

Afectado por Incidentes
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

dragon-ai-agent

Incidents implicated systems
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

curation-scanner workflow

Incidents implicated systems
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

Claude Code

Incidents implicated systems
  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

AI agent systems

Incidents implicated systems
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

  • Incidente 1470
    1 Report

    DisMech AI Curation Agent Reportedly Completed GitHub Issue Intended as New Contributor's Learning Task

Más
Entity

Irregular

Incidents involved as Deployer
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

AI evaluation organizations

Incidents involved as Deployer
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

AI agent system deployers

Incidents involved as Deployer
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

Large language model developers

Incidents involved as Developer
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

AI agent system developers

Incidents involved as Developer
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

Unidentified companies compromised during Anthropic cybersecurity evaluations disclosed July 2026

Afectado por Incidentes
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

Companies

Afectado por Incidentes
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

Large language models

Incidents implicated systems
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

Más
Entity

Claude

Incidents implicated systems
  • Incidente 1627
    16 Report

    Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

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

Project and Community test

  • Acerca de
  • Contactar y Seguir
  • Aplicaciones y resúmenes
  • Guía del editor
  • RAIC AIID Taxonomy Policy

Incidencias

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

2023 - AI Incident Database

  • Condiciones de uso
  • Política de privacidad
  • 2a25224