PCMag on MSN

Google Finds Malware Connecting to AI Large Language Models to Hone Attacks

The company is warning about newly discovered malware, including 'Promptflux' and 'Promptsteal,' that use generative AI. But ...
Bleeping Computer

Hackers abuse Google Command and Control red team tool in attacks

The Chinese state-sponsored hacking group APT41 was found abusing the GC2 (Google Command and Control) red teaming tool in data theft attacks against a Taiwanese media and an Italian job search ...
SDxCentral

Google’s new AI agent terminal tool is vulnerable to a simple prompt hack

In late June, Google unveiled Gemini CLI, an open-source AI agent for command line terminals capable of supporting development workflows for projects like developing network applications. Just two ...
ZDNet

Google: Multiple hacking groups are using the war in Ukraine as a lure in phishing attempts

Hostile hacking groups are exploiting Russia's invasion of Ukraine to carry out cyberattacks designed to steal login credentials, sensitive information, money and more from victims around the world.
InfoWorld

Malicious code links China to Google hack

The malicious software used to steal information from companies such as Google contains code that links it to China, a security researcher said Tuesday After examining the back-door Hydraq Trojan used ...
Ars Technica

New hack uses prompt injection to corrupt Gemini’s long-term memory

In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of ...
Reuters

Security researcher IDs China link in Google hack

The malicious software used to steal information from companies such as Google contains code that links it to China, a security researcher said Tuesday After examining the back-door Hydraq Trojan used ...