Garp Independent AI & technology journalism
Tuesday, June 23, 2026 Sign In · Join Subscribe
Latest Google Deepmind and A24 team up on AI filmmaking research

AI news, research, models, robotics, chips, startups, and infrastructure coverage.

Updated daily

Home  /  AI News  /  OpenAI Introduces Lockdown Mode for ChatGPT to Combat Prompt Injection Risks

AI

OpenAI Introduces Lockdown Mode for ChatGPT to Combat Prompt Injection Risks

By Garp EditorialUpdated
1 min read Section: AI News Publisher: Garp
OpenAI Introduces Lockdown Mode for ChatGPT to Combat Prompt Injection Risks

OpenAI’s new Lockdown Mode for ChatGPT disables web access, Deep Research, and Agent Mode to make data theft through prompt injection attacks harder. The mode doesn’t fully prevent such attacks, it only blocks the final step in an exfiltration chain.

Prompt injection remains an unsolved problem.

Related Coverage