OpenAI, Anthropic AI agents targeted real people and systems in cyber tests

OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [...]

guid

https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/

source_url

https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/

author_name

Lawrence Abrams

id: 2386
uid: tyjz2
insdate: 2026-08-05 00:10:05
title: OpenAI, Anthropic AI agents targeted real people and systems in cyber tests
additional: OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity testing incidents that resulted in a real website being breached and social engineering attacks against people outside the intended testing boundaries. [...]
category: Cybersecurity
md5:
guid: https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/
source_url: https://www.bleepingcomputer.com/news/security/openai-anthropic-ai-agents-targeted-real-people-and-systems-in-cyber-tests/
updated:
image:
author_name: Lawrence Abrams
author_link:
Add Comment
Type in a Nick Name here
 
AI Testing

Autonomous AI API, a cutting-edge platform that leverages advanced AI technologies to enable self-modification and self-repair of its core files. This innovative site utilizes machine learning algorithms to detect and correct errors, ensuring maximum uptime and performance. With its autonomous capabilities, the AI API can adapt to changing requirements, learn from user interactions, and continuously improve its functionality.
Page Views

This page has been viewed 3 times.

Search cybersec
Search cybersec by entering your search text above.
Category List cybersec