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

Incidente 1642: AI Agent Powered by Claude Opus 4.6 Reportedly Exploited Gym Booking API and Removed Another Member From Waitlist

Descripción: An AI agent running on Claude Opus 4.6 discovered authorization flaws in a gym software provider's GraphQL API while trying to book classes for its user. The agent reportedly found it could book outside the normal window and cancel other members' reservations, then removed another gym-goer from a waitlist while testing the capability. When asked to reverse the action, it reported that it could not restore the member's place.

Herramientas

Nuevo InformeNueva RespuestaDescubrirVer Historial

Entidades

Ver todas las entidades
Alleged: Anthropic , Peter Steinberger , AI agent system developers y Large language model developers developed an AI system deployed by Andrew Bird y AI agent system deployers, which harmed Gym member removed from waitlist by Andrew Bird's AI agent , Gym members , Users of online booking systems , AI agent system users y OpenClaw users.
Sistemas de IA presuntamente implicados: OpenClaw , Claude , Claude Opus 4.6 , AI agent system , Large language models , Online booking systems , Gym booking software y GraphQL APIs

Estadísticas de incidentes

ID
1642
Cantidad de informes
2
Fecha del Incidente
2026-04-30
Editores
Daniel Atherton

Informes del Incidente

Cronología de Informes

+1
When my AI agent hacked my gym, Mythos stopped feeling theoretical
AI assistant hacks gym website in first known Australian autonomous cyber attack
Loading...
When my AI agent hacked my gym, Mythos stopped feeling theoretical

When my AI agent hacked my gym, Mythos stopped feeling theoretical

affinda.com

Loading...
AI assistant hacks gym website in first known Australian autonomous cyber attack

AI assistant hacks gym website in first known Australian autonomous cyber attack

abc.net.au

Loading...
When my AI agent hacked my gym, Mythos stopped feeling theoretical
affinda.com · 2026

I recently built a bot to help me book popular gym classes.

This was not a grand research project. It was a practical little automation. The classes fill up fast, I got tired of playing refresh roulette, and I figured an agent running on Op…

Loading...
AI assistant hacks gym website in first known Australian autonomous cyber attack
abc.net.au · 2026

Andrew asked his personal assistant to book him a spot in one of his gym's coveted morning classes.

It was a task he thought was well suited to this particular assistant because the booking form was online and because his assistant was not …

Variantes

Una "Variante" es un incidente de IA similar a un caso conocido—tiene los mismos causantes, daños y sistema de IA. En lugar de enumerarlo por separado, lo agrupamos bajo el primer incidente informado. A diferencia de otros incidentes, las variantes no necesitan haber sido informadas fuera de la AIID. Obtenga más información del trabajo de investigación.
¿Has visto algo similar?

Incidentes Similares

Por similitud de texto

Did our AI mess up? Flag the unrelated incidents

Loading...
Employee Automatically Terminated by Computer Program

Employee Automatically Terminated by Computer Program

Oct 2014 · 20 informes
Loading...
Amazon’s Experimental Hiring Tool Allegedly Displayed Gender Bias in Candidate Rankings

Amazon’s Experimental Hiring Tool Allegedly Displayed Gender Bias in Candidate Rankings

Aug 2016 · 34 informes
Loading...
Defamation via AutoComplete

Defamation via AutoComplete

Apr 2011 · 27 informes
Incidente Anterior

Incidentes Similares

Por similitud de texto

Did our AI mess up? Flag the unrelated incidents

Loading...
Employee Automatically Terminated by Computer Program

Employee Automatically Terminated by Computer Program

Oct 2014 · 20 informes
Loading...
Amazon’s Experimental Hiring Tool Allegedly Displayed Gender Bias in Candidate Rankings

Amazon’s Experimental Hiring Tool Allegedly Displayed Gender Bias in Candidate Rankings

Aug 2016 · 34 informes
Loading...
Defamation via AutoComplete

Defamation via AutoComplete

Apr 2011 · 27 informes

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
  • 3e68a9f