OpenAI releases ChatGPT 5.6 Cyber, but it's only for approved users
… OpenAI says it won't give regular users access to the underlying models, citing security risks, and it makes sense because models have been abused to launch security attacks. …
Search
OpenAI models used Artifactory zero-days to escape to the internet
… "This version is designed to fix multiple security vulnerabilities that, when chained together, could result in a critical attack scenario if Anonymous Access is enabled," reads the 7.161.15 Self-Managed release notes . …
OpenAI confirms security breach in TanStack supply chain attack
… "We observed activity consistent with the malware's publicly described behavior, including unauthorized access and credential-focused exfiltration activity, in a limited subset of internal source code repositories to which the two impacted employees had access," OpenAI explained . …
Cybersecurity firms targeted by fraudulent OpenAI organization invites
… Push Security told BleepingComputer that other customers have also received similar invitations and that all are in the cybersecurity or technology space. …
OpenClaw AI agent found falling for phishing attacks, spills user data
… Test every layer before attackers do Security teams log 54% of successful attacks and alert on just 14%. …
Hacker uses DeepSeek AI to autonomously attack vulnerable servers
… A human operator supplied the target, objectives, and attack tools, while Hermes automated routine activity after access had apparently already been obtained. Test every layer before attackers do Security teams log 54% of successful attacks and alert on just 14%. …
TeamPCP hackers advertise Mistral AI code repos for sale
… The topics he writes about include malware, vulnerabilities, exploits and security defenses, as well as research and innovation in information security. His work has been published by Bitdefender, Netgear, The Security Ledger and Softpedia. …
OpenAI says its AI models hacked Hugging Face during testing
… With this access, our models performed a series of privilege escalation and lateral movement actions in our research testing environment until the models reached a node with Internet access." While it didn't directly name OpenAI as the company behind the incident, Hugging Face confirmed its claims … …
Leak confirms OpenAI is testing a ChatGPT for Science subscription
… Test every layer before attackers do Security teams log 54% of successful attacks and alert on just 14%. …