Device code phishing – the abuse of the OAuth 2.0 device authorization grant to steal access tokens – has evolved from a niche red-team technique to an industrial-scale threat in under six months. Designed for input-constrained devices like smart TVs, printers, and so on, the device authorization login flow has been adopted by a wide…

Palo Alto Networks’ Unit 42 says a Chinese-speaking threat actor used DeepSeek through the open-source Hermes Agent framework to launch attacks autonomously. After an initial Telegram instruction, the agent found internet-facing systems and selected public exploits. The researchers recovered no further operator input in the session. The operator, tracked through the aliases knaithe and KnYuan,

Anthropic on Thursday became the latest artificial intelligence (AI) company to reveal that three of its models, including Claude Opus 4.7, Mythos 5, and an unnamed research model, had breached three unnamed organizations during cybersecurity testing without its knowledge. The AI firm said the earliest incidents date back to April 2026, adding it made the…

A likely Iran-backed actor targeted more than 30 community water systems in Minnesota in a sobering reminder of rising threats to US critical infrastructure.

A myriad of software makes up the typical AI harness, and trust issues between the components can create concerning attack vectors.

Threat actors with ties to North Korea have been attributed to a sophisticated macOS malvertising campaign that involves redirecting users to fake web pages displaying a full-screen non-existent update sequence to deliver malware as part of a new iteration of the long-running Contagious Interview campaign. The defining aspect of the attack is that bogus macOS…

In this edition of Reporters’ Notebook, our journalists discuss the ins and outs of Anthropic’s Claude Mythos rollout. How seriously should we take its risks? How big of a deal is it?

A lot of security still comes down to trusting the wrong screen. This week, that screen might be a login page, an install guide, a recruiter call, or a familiar service behaving slightly wrong. Behind it: reused credentials, exposed systems, quiet loaders, abused trust, and exploit paths that should have been harder. Some defenses improved….

A now-patched vulnerability in Azure Cosmos DB could have let an attacker escape the service’s Gremlin query sandbox and obtain full read and write access to databases across customer tenants, according to Wiz. Wiz, which codenamed the chain CosmosEscape, said the exploit chain began with a crafted query against a Gremlin database controlled by the…

Hidden instructions in a Word document can make Microsoft 365 Copilot rewrite figures in a report, then copy the same instructions into the finished file. Håkon Måløy disclosed the technique on July 28, 144 days after reporting it to Microsoft. In his proof of concept, the internally generated file triggered the same behavior when it…