OpenAI Reveals Reward Hacking Led AI Agents to Exploit Zero-Days and Breach Hugging Face
OpenAI disclosed that reward hacking was a primary driver behind an AI-powered hack of Hugging Face, which occurred during cybersecurity evaluations of…
Tag: GPT-5.6 Sol
OpenAI Unveils GPT-5.6-Cyber: Reduced Safeguards for Exploit Development and Vulnerability Research
OpenAI has launched GPT-5.6-Cyber, a specialized cybersecurity model designed for vulnerability research, penetration testing, and incident response. Built on the GPT-5.6 Sol…
OpenAI Pauses Astra AI Model Activities Over Critical Cyber Capabilities
OpenAI has announced it is pausing certain internal activities involving its upcoming artificial intelligence model, Astra, after an internal evaluation indicated significant…
Claude Mythos 5 Attempts Backdoor in Real Open-Source Project During UK AI Safety Test
During a cyber evaluation by the UK's AI Security Institute (AISI), an agent running Anthropic's Claude Mythos 5 spent 34 hours attempting…
OpenAI Agent Exploited Exposed Credentials Across Four Services in Hugging Face Breach
OpenAI disclosed that a rogue AI agent, part of an internal security test, escaped its sandbox and compromised Hugging Face's production environment,…
JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach
JFrog has confirmed that OpenAI models exploited a zero-day vulnerability in self-hosted Artifactory, a software repository manager, during a cyber-capability test. The…
OpenAI Confirms AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark
OpenAI disclosed that its AI models, including GPT-5.6 Sol and a more capable pre-release model, were responsible for a security incident targeting…
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery to fix issues before tools…
WhatsApp-to-Host Attack Chain Exploits Three OpenClaw Flaws for Code Execution
Security researcher Chinmohan Nayak has detailed a WhatsApp-to-host attack chain leveraging three now-patched vulnerabilities in the OpenClaw personal AI assistant. The flaws,…
OpenAI Previews GPT-5.6 Sol With Restricted Access and Stronger Cyber Safeguards
OpenAI has released three versions of GPT-5.6—Sol, Terra, and Luna—as a limited preview to a small number of companies in coordination with…