Particle.news
Download on the App Store

OpenAI’s ChatGPT Atlas Launch Faces Early Security Probes as Rapid Updates Line Up

Prompt‑injection findings are already shaping OpenAI’s safety messaging, with near‑term product fixes pledged.

Overview

  • OpenAI released ChatGPT Atlas as an AI‑native browser with an integrated agent mode that can perform tasks for users, initially for paying subscribers.
  • Security researchers demonstrated prompt‑injection tricks against Atlas, including forcing responses like “Trust No AI,” and The Register reported replicating the attack.
  • Brave warned that AI browsers are broadly vulnerable to indirect prompt injection, while developers shared examples of traps and jailbreaks that exploit agent actions.
  • OpenAI detailed guardrails for agent mode and cautioned risks persist, with its CISO calling prompt injection an unsolved security problem despite red‑teaming and new defenses.
  • Product lead Adam Fry outlined near‑term additions such as multiprofile support, tab groups, an opt‑in ad blocker, a model picker, and agent reliability improvements, as Atlas also showcases new UI ideas like scrolling tabs.