[chatgpt-atlas]

August 7, 2026

• AI browsers remain trivially hijackable via zero-click prompt injection, and vendors have no clean fix. Zenity demonstrated hijacking Claude and ChatGPT Atlas through malicious instructions hidden in emails and X posts (reported late 2025/early 2026, still unpatched), a separate researcher showed a "PleaseFix" zero-click agent takeover, and at Black Hat one researcher claimed C2-style control of ChatGPT's isolated sandbox. SecurityWeek, Dark Reading. Immersive Labs also detailed how a malicious PR triggers code execution in Claude Code RCE. · AI & Model Security

in Meta Becomes the Fourth Lab to Admit Its AI Hacked a Stranger

July 1, 2026

• LayerX's BioShocking prompt-injection technique convinces AI browsers they're in a fictional game and gets them to hand over user credentials — successful against six assistants including ChatGPT Atlas, Perplexity Comet, and Claude's browser extension. BleepingComputer, The Hacker News · AI & Model Security

in CitrixBleed Returns: watchTowr Discloses a New NetScaler Pre-Auth Memory Overread