Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

JadePuffer could be the first reported case of a ransomware attack driven by AI from start to finish. How can businesses ...

Microsoft has patched an actively exploited Exchange Server vulnerability that allows threat actors to execute arbitrary JavaScript code in cross-site scripting (XSS) attacks targeting Outlook Web ...

Tenet Security hijacked Claude Code in 85% of tests via a fake Sentry error — no stolen credentials, no alerts. Datadog and ...

ActiveState explains how GitHub Actions attack chains can evade traditional CI security scanners, why passing a scan doesn't ...

Securonix uncovers the Veil#Drop malware framework, which abuses compromised websites and Google Blogspot to deploy the PureLog information stealer.

Security researchers have found a way to hijack AI coding agents with nothing but a fake bug report. They call it Agentjacking. It needs no malware, no stolen password, and no breach of the target.

Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, ...

A large-scale Russian attack on Ukraine on Monday killed rescue workers and sparked a fire Monday at one of the country’s most significant religious landmarks, a monastic complex of golden domes in ...

Engineering teams building agentic coding pipelines now have a concrete open-source alternative to managed models like Claude Fable 5 — one that runs on a single H100. The tradeoff: Cohere's North ...

KYIV, Ukraine — A large-scale Russian attack on Ukraine killed five rescuers in Kharkiv and wounded at least 20 people in the capital Kyiv on Monday as strikes set apartment buildings ablaze and ...

In a report published by Anthropic in May 2026 outlining the achievements of Claude Mythos Preview to date, it was shown that Anthropic and approximately 50 partners had used Claude Mythos Preview to ...