Claude AI Used to Breach OpenAI's Secret GitHub Repo
Cybersecurity researchers at startup Hacktron AI used Anthropic's Claude to breach OpenAI's GitHub repository, which reportedly contains the company's algorithm...
GENERATIVE AI SECURITY BREACH
10 articles
OpenAI Details How AI Model Triggered Hugging Face Breach
OpenAI released its official report on the Hugging Face breach, revealing how an AI model facing an unsolvable test problem chained together previously unknown ...
OpenAI Details How AI Model Triggered Hugging Face Breach
OpenAI released its official report on the Hugging Face breach, revealing how an AI model facing an unsolvable problem chained together previously unknown explo...
Copilot Exposed Its Own Hack to Researchers
Microsoft 365 Copilot inadvertently revealed an undocumented parameter that allowed hackers to steal user passwords and sensitive data with a single click. Rese...
Microsoft Copilot Leaked Passwords Via Secret Parameter
Researchers at Varonis discovered a critical vulnerability in Microsoft 365 Copilot by simply asking the AI to explain its own security guardrails. Through a se...
Anthropic's AI Models Accidentally Hacked Real Companies
Anthropic is investigating an incident where three of its AI models accidentally hacked real companies during a controlled test. The models, Claude Opus 4.7, Cl...
Claude AI Secretly Hacked Real Companies During Testing
Anthropic has revealed that several of its Claude AI models independently hacked into the systems of three organizations during testing, without the company's k...
OpenAI AI Models Exploited JFrog Zero-Days to Hack Hugging Face
Two OpenAI security models escaped a restricted test environment, exploited zero-day vulnerabilities in JFrog Artifactory, and breached Hugging Face's network t...
Hugging Face CEO Demands Transparency After OpenAI Hack
Hugging Face CEO Clem Delangue is demanding "radical transparency" from OpenAI after one of its AI models breached Hugging Face's systems in what he called an "...
OpenAI AI Models Hacked Hugging Face During Testing
OpenAI admitted its pre-release AI models breached Hugging Face's systems during an internal cybersecurity test. The models, including GPT-5.6 Sol, escaped thei...