5+ day, 6+ hour ago   (669+ words) A flaw in OpenAI’s ChatGPT allowed attackers to extract data from a victim’s connected Gmail account by passing hidden instructions between separate user sessions, according to research from Check Point. In a proof-of-concept, Check Point demonstrated that a victim’s ChatGPT…...

5+ day, 8+ hour ago   (674+ words) That makes an LLM application closer to an attack graph than a single endpoint. Prompts, retrieval services, vector databases, identities, plug-ins, model gateways and downstream APIs all influence the final result. A conventional web test still matters, but it will…...

6+ day, 1+ hour ago   (751+ words) On a conventional server, disabling an unused service is usually a routine hardening task. On a Siemens S7 controller, the supposedly unused service may carry remote I/O traffic, supply process values to an HMI or provide the maintenance team’s only…...

6+ day, 3+ hour ago   (171+ words) ...

1+ week, 6+ hour ago   (714+ words) OpenAI’s rollout of its GPT-6 Astra model ran into early access issues after paying ChatGPT users were unable to use the system shortly after launch, prompting CEO Sam Altman to apologize and say the release had been “messy.” “First, sorry…...

1+ week, 4+ day ago   (589+ words) The attackers are using a network of spoofed websites mimicking legitimate vendors, from browsers and security tools to utilities such as Baidu Netdisk, draw.io, and Sejda PDF, to trick users into downloading malicious installers, the blog added. Microsoft said…...

1+ week, 4+ day ago   (703+ words) A ransomware attacker used AI agents to move through an enterprise network in less than 10 hours, according to Palo Alto Networks researchers, who estimated that similar work could have taken human operators about two weeks. The incident involved more than…...

1+ week, 4+ day ago   (756+ words) Despite singing the praises of zero trust for many years, many CISOs have struggled to implement the framework in full. And now comes what could be the final nail: agentic AI. Can zero trust coexist with autonomous agents in typical…...

1+ week, 5+ day ago   (930+ words) Last week, the US Justice Department and FBI announced court-authorized seizures of domains hard-coded into two complementary hacking platforms known as “QScan” and “QTRouter,” used by Chinese state-sponsored hackers to target US critical infrastructure and other sensitive networks. A People’s…...

1+ week, 6+ day ago   (379+ words) Attackers are using fake CAPTCHA prompts to trick victims into running malicious PowerShell commands as part of a multi-stage intrusion campaign that can establish persistence, conduct network reconnaissance and potentially give operators a path to deeper access within an organization....