LLM

Glowing digital skull showing prompt injection attack on LLMs

“Man in the Prompt”: New Class of Prompt Injection Attacks Pairs With Malicious Browser Extensions to Issue Secret Commands to LLMs

August 4, 2025

A new theoretical attack described by researchers with LayerX lays out how frighteningly simple it would be for a malicious or compromised browser extension to intercept user chats with LLMs and insert prompt injection attacks designed to exfiltrate data without the target being aware.

Access granted message on screen showing Russian malware with LLM

Cyber Security News

Russian Malware Found Using LLM To Issue Real-Time Commands

July 23, 2025

A new Russia-based family of malware has been observed using a large language model (LLM) to issue commands on compromised systems in real time, which can potentially improve attacker capability by allowing them to shift tactics during an attack without having to introduce new payloads.

LLM

“Man in the Prompt”: New Class of Prompt Injection Attacks Pairs With Malicious Browser Extensions to Issue Secret Commands to LLMs

Russian Malware Found Using LLM To Issue Real-Time Commands

Tata Electronics Data Leak Exposes Apple iPhone Pro Supplier List, Parts, and Photos

Apple Steps Up Release of Security Updates in Response to AI Hacking Threats

Several ISPs and Millions of Customers Compromised in KDDI’s Email System Data Breach

Security Breach at Tata Electronics Affects Apple, Tesla, and Other Technology Giants