Cyber Security
Agentjacking tricks AI coding agents into running malicious code via fake Sentry error reports. Learn how this exploit works and how to protect your code.
DirtyDecrypt (CVE-2026-31635) is a Linux kernel vulnerability causing local privilege escalation via the rxgk pagecache and missing COW guards.
The Hades Campaign is a sophisticated worm targeting Python developers. It uses adversarial prompt injection to trick AI security tools and steals data.
Researchers demonstrate a self-replicating AI worm using local, open-weight models, bypassing traditional security to spread via semantic overflows.
Meta blocks new NSO Group phishing attacks on WhatsApp and files a contempt order for violating a permanent injunction against the spyware vendor.
OpenAI introduces Lockdown Mode to protect ChatGPT users from prompt injection and data exfiltration. Learn how this setting secures sensitive data.
AI-powered autonomous worms are rewriting the rules of lateral movement. This briefing explores how CISOs must adapt to machine-speed exploitation.
Hackers tricked Meta's AI chatbot to hijack high-profile Instagram accounts. Learn how prompt engineering bypassed security and how to protect your data.
See you on the other side.
Our end-to-end encrypted email and cloud storage solution provides the most powerful means of secure data exchange, ensuring the safety and privacy of your data.
/ Create a free account
