AI agent hacked McKinsey chatbot for read-write access
Security AI vs AI: Agent hacked McKinsey's chatbot and gained full read-write access in just two hours David and Goliath…but with AI agents Researchers at red-team security startup…
The problem is almost entirely due to Meta's customer support now being run by AI. The tech giant made the switch back in March, saying it would enable "24/7 help for account issues like updating your password and settings for your profile." But with the AI chatbot handling the whole process, humans couldn't step in when suspicious activity began. That allowed hackers to carry out the social engineering-style attack and pull it off multiple times before anyone noticed. Per Cybersecurity News, security researchers ZachXBT and Dark Web Informer were the first to publicly expose the exploit, but
Instagram's AI Chatbot Gave Away a Bunch of Accounts to HackersSecurity AI vs AI: Agent hacked McKinsey's chatbot and gained full read-write access in just two hours David and Goliath…but with AI agents Researchers at red-team security startup…
…Social engineering scams are getting even more sophisticated in the age of AI, too. A few months ago, another scheme was found, where hackers would pose as CEOs with deepfake technology and…
…AI coding apps, including Claude Code, Gemini CLI, VS Code, and Cursor. The security firm Cloudsmith , malware analysis site OpenSourceMalware , and 404 Media were among the first to report the hack. For…
…This will stop people potentially hacking into your accounts via your AI agent. And always commit to local backups. With ransomware becoming more autonomous, maintain an immutable offline backup through an external…
Instagram accounts hacked using Meta AI
Meta says hackers can no longer access accounts through its AI chatbot
Hackers likely hijacked over 20k Instagram accounts with Meta's AI chatbot
Meta says roughly 20,000 Instagram accounts may have been hacked in a recent attack abusing an AI-powered account recovery support tool.
Meta confirms 1000s of Instagram accounts were hacked by abusing its AI chatbot
Nearly a week after the makers of the popular web server management software cPanel and WebHost Manager (WHM) alerted users of a critical flaw in its software, hackers are now mass-compromising…
WhatsApp said that it disrupted a new hacking campaign linked to NSO Group , a spyware maker that has been ensnared in countless cases of abuse all over the world. The messaging app…
…What hackers could do Once Gemini ingested the poisoned notification, the researchers found they could force the AI assistant into executing an alarming array of unauthorized tasks without giving the user any…
…The vulnerability reportedly stems from a loophole that allows hackers to access an account using only one transaction ID from the target account. Hackers are somehow obtaining a single transaction ID linked…
…Hackers used AI to develop zero-day exploit for web admin tool Actively Exploited Authentication Bypass Initial Access Broker MFA Ransomware SonicWall SSL VPN Vulnerability Bill Toulas Bill Toulas is a tech…
…The hacking and extortion gang ShinyHunters claimed responsibility for the breach. The hackers claim to have stolen students’ names, their personal email addresses, and messages sent between teachers and students — the same…