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 ...
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 ...
Santa Rosa Press Democrat

In-N-Out’s fake secret menu ‘hacks’ prompt rare response from owner

For every viral TikTok post claiming to have discovered some wild new In-N-Out hack, there are hundreds of actual, real-life In-N-Out employees who then have to deal with the fallout. We’re talking ...