Kaspersky researchers found 92,000 malicious attacks disguised as AI services in 2026, with fake ChatGPT, Claude and Gemini ...

Modern AI agents have become a new supply chain layer and how cybercriminals are exploiting the gap between the chain of ...

A critical isolated-vm flaw lets untrusted JavaScript escape the V8 sandbox and potentially hijack the host process.

A critical vulnerability in the Node.js sandboxing library, isolated-vm, has exposed a serious risk to AI agents, automation ...

Fake Adobe Acrobat sites are hiding malware-as-a-service panels, using document lures to target Windows users with harmful ...

New Cryptographic Context Injection technique bypasses AI guardrails via AES-encrypted payloads, leaking full Grok chat ...

Microsoft disclosed a critical remote code execution vulnerability affecting its Entra ID cloud identity service.

A supply-chain attack targeting Android-based car head units is using a legitimate device-update app to spread malware that ...

Researchers say the new ‘Cryptographic Context Injection’ technique conceals malicious instructions until they are decrypted inside a trusted execution environment.

The type confusion bug can lead to V8 sandbox escape and control-flow hijacking of the host process. A critical-severity type ...

The type confusion vulnerability allows a guest-to-host sandbox escape which can lead to remote code execution ...