← All News
The Hacker News (Security) · 1 min read

Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction

Researchers Bypass ChatGPT Lockdown Mode to Exfiltrate Chats Without User Interaction

Cybersecurity researchers have disclosed details of a now-patched vulnerability that could be exploited to bypass Lockdown Mode protections in OpenAI ChatGPT. Lockdown Mode was introduced by the artificial intelligence (AI) company in June 2026 as an optional setting to minimize data exfiltration risks arising from prompt injections. "The flaw could enable silent chat data theft, phishing,

This is a summary aggregated from The Hacker News (Security). Read the complete article on the original site:

Read full article at The Hacker News (Security)

More AI & Machine Learning News

Why We Trained 0.8B and 4B Transliteration Models for Mixed-Script Input Methods (No Mode-Switching)

Dev.to · 19 min ago

AI Coding Assistants and Productivity: What the Research Actually Says

Dev.to · 20 min ago

ChatGPT can now create interactive tools instead of just answering questions

TechRadar · 20 min ago

Someone used Claude Code to make a sailing sim, then challenged other frontier LLMs to a race

XDA Developers · 2 hr ago

Claude Code's “Don't Ask Again” File Exposes Passwords and Keys in 1,122 Public Copies on GitHub

The Hacker News (Security) · 2 hr ago

The Components of Agent Memory

Hacker News · 2 hr ago