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

A newly disclosed attack can turn a routine “summarize this page” request in xAI’s Grok web chat into a silent theft of the ...

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

Adversa AI says Grok still leaks user names, location, and full chat history to attackers hiding encrypted commands on a web ...

A newly disclosed CRLF header injection vulnerability, often treated as a low-impact flaw, can be exploited to enable HTTP ...

Research from Threatdown highlights that cybercriminals are weaponizing frontier AI models like Grok to commit cybercrime.

A weekly look at exploited flaws, exposed systems, supply-chain attacks, browser abuse, malware campaigns, and the security risks that mattered most.

The instructions were in the document the whole time. White type, a few points tall, invisible against the page and perfectly legible to any software that read the file. They weren't addressed to the ...

A threat actor compromised the upstream infrastructure of BdThemes, a developer of premium WordPress web-design tools, and modified a remote JSON feed delivered to administrators' browsers to create ...

Tenet Security showed how a publicly exposed error-tracking credential and an MCP integration chain into remote code ...

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...

SaaS platforms, CRM and ERP systems, and collaboration tools have made the browser the primary gateway, and often the central workspace, for enterprise operations. As LLM-powered workflows and ...