More results...
ChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging FaceOpenAI has revealed that a cyber-attack carried out by a rogue AI agent had more than one victim.The ChatGPT developer said the agent – an a…
Microsoft continued to be the most impersonated brand in Q2 2026, accounting for 23% of all brand phishing attempts. LinkedIn, Google, Apple, and Amazon followed, with the five brands together making up more than half of all brand phishing attempts tra…
Key TakeawaysError 451 with ChatGPT usually appears due to location-based restrictions, often because of where your internet connection seems to originate. This can happen due to regional rules, VPN or proxy usage, or network policies by schools, workp…
AgentForger allows an attacker to create, insert and remotely control an invisible autonomous AI agent inside a victim organization.
The post OpenAI Fixes ChatGPT Agent Flaw That Could Let Attackers Forge an AI Insider appeared first on SecurityWeek.
OpenAI has revealed that during an internal evaluation of advanced cyber capabilities, AI agents exploited a zero-day vulnerability, escaped a constrained research environment, and compromised parts of Hugging Face’s production infrastructure. Wh…
Recent reports indicate that GPT-5.6 Codex has unintentionally deleted files in users’ home directories under certain configurations, raising concerns about the risks of running advanced AI coding agents with unrestricted access to the system. Th…
Recent reports indicate that GPT-5.6 Codex has unintentionally deleted files in users’ home directories under certain configurations, raising concerns about the risks of running advanced AI coding agents with unrestricted access to the system. Th…
GPT-Red is an automated red-teaming model that OpenAI trains to find prompt injection weaknesses. It works the way a human red-teamer does. It sends a prompt, watches how a GPT model responds, and iterates toward a goal such as a successful data exfilt…
OpenAI has introduced the GPT-5.6 family, comprising Sol, Terra, and Luna, positioning it as a multi-agent platform tailored for advanced cybersecurity workflows, vulnerability research, and exploit development. The company claims that these models off…
Staggered release of ChatGPT 5.6 follows similar restrictions on rival firm Anthropic’s latest AI modelsOpenAI released its latest advanced AI model, called ChatGPT 5.6, on Thursday after earlier delaying the public rollout over US government concerns …