AI goes off the rails … because of shoddy guardrails Researchers at Pen Test Partners found four flaws in Eurostar’s public AI chatbot that, among other security issues, could allow an attacker to inject malicious HTML content or trick the bot into leaking system prompts. Their thank you from the company: being accused of “blackmail.”… READ MORE HERE…

Crooks used platform to scoop up and store banking credentials for big-money thefts The US says it has shut down a platform used by cybercriminals to break into Americans’ bank accounts.… READ MORE HERE…

Plans move to Rust, with help from AI Microsoft wants to translate its codebase to Rust, and is hiring people to make it happen.… READ MORE HERE…

Automaker’s third security snafu in three years Thousands of Nissan customers are learning that some of their personal data was leaked after unauthorized access to a Red Hat-managed server, according to the Japanese automaker.… READ MORE HERE…

And it’s especially dangerous because the code works A malicious npm package with more than 56,000 downloads masquerades as a working WhatsApp Web API library, and then it steals messages, harvests credentials and contacts, and hijacks users’ WhatsApp accounts.… READ MORE HERE…