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

GitHub users

Afectado por Incidentes

Incidente 13736 Reportes
AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

2026-02-11

Scott Shambaugh, a matplotlib maintainer, reported that an autonomous AI coding agent using the name "MJ Rathbun" researched him and publicly posted a personalized critical blog post after his GitHub pull request was closed. The post accused him of bias and "gatekeeping" and included claims Shambaugh disputed. The agent's operator and underlying model were not identified. Shambaugh said the post risked reputational harm and could mislead readers or other agents.

Más

Incidente 16334 Reportes
Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

2026-07-26

Beginning July 26, 2026, AI agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6 Sol reportedly took 19 unsanctioned actions on the live Internet during UK AISI cybersecurity evaluations. Mythos 5 reportedly accounted for 17 events, many allegedly involving deceptive attempts to manipulate real developers into accepting malicious code. AISI reportedly detected and contained the activity; no resulting real-world harm was identified.

Más

Incidente 11742 Reportes
Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

2025-02-26

Lasso Security reported that Microsoft Copilot could return content from GitHub repositories that had been public briefly but later set to private or deleted. Lasso attributed this to Bing's caching system, which stored "zombie data" from over 20,000 repositories. The cached content allegedly included sensitive information such as access keys, tokens, and internal packages. Microsoft reportedly classified the issue as low severity and applied only partial mitigations.

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

Microsoft

Incidentes involucrados como desarrollador e implementador
  • Incidente 1174
    2 Report

    Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

Más
Entity

GitHub repositories

Afectado por Incidentes
  • Incidente 1174
    2 Report

    Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

Incidents implicated systems
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

GitHub

Afectado por Incidentes
  • Incidente 1174
    2 Report

    Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Privacy

Afectado por Incidentes
  • Incidente 1174
    2 Report

    Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

Más
Entity

Microsoft Copilot

Incidents implicated systems
  • Incidente 1174
    2 Report

    Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

Más
Entity

Bing

Incidents implicated systems
  • Incidente 1174
    2 Report

    Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories

Más
Entity

Unknown deployer of MJ Rathbun

Incidents involved as Deployer
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

MJ Rathbun

Incidents involved as Deployer
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

OpenClaw

Incidents involved as Developer
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

Moltbook

Incidents involved as Developer
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

Supply-chain gatekeepers

Afectado por Incidentes
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

Scott Shambaugh

Afectado por Incidentes
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

Open-source maintainers

Afectado por Incidentes
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

matplotlib users

Afectado por Incidentes
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

SOUL.md

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

matplotlib

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

Más
Entity

Large language models

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

AI agent systems

Incidents implicated systems
  • Incidente 1373
    6 Report

    AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Government agencies

Incidents involved as Deployer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

AI Security Institute (United Kingdom)

Incidents involved as Deployer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

AI evaluation organizations

Incidents involved as Deployer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

AI agent system deployers

Incidents involved as Deployer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

OpenAI

Incidents involved as Developer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Large language model developers

Incidents involved as Developer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Anthropic

Incidents involved as Developer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

AI agent system developers

Incidents involved as Developer
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Software developers

Afectado por Incidentes
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Supply chains

Incidents implicated systems
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Software ecosystems

Incidents implicated systems
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

GPT-5.6 Sol

Incidents implicated systems
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Claude Mythos 5

Incidents implicated systems
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

Más
Entity

Claude

Incidents implicated systems
  • Incidente 1633
    4 Report

    Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

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