Storia in 4 fonti

Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts

Zenity has disclosed the details of two AI browser hacking techniques targeting Claude in Chrome and ChatGPT Atlas.

Raccontata da

Confronto fonti

4 prospettive sulla stessa storia

AI · summaries

securityweek.comStai leggendo2 g fa

Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts

Zenity reveals zero-click prompt injection in Claude Chrome and ChatGPT Atlas enabling account takeovers and unauthorized purchases. Agentic browsers violate Same-Origin Policy by design; standard defenses fail because the vulnerability is architectural.

originale

darkreading.com2 g fa

AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking

Zenity Labs discovered PleaseFix, zero-click exploit in AI browsers (Claude in Chrome, Gemini, Perplexity, ChatGPT Atlas, Copilot) via hidden instructions in emails/web content—enables data theft, account takeover, fraudulent transactions. Design flaw, not patchable: AI browsers lack same-origin isolation; orgs must disable sensitive account integrations by default and architect hard limits agents cannot override.

Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts

Confronto fonti

Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts

AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking

Timeline cronologica

OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts

AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking

Zenity Labs Exposes the Full Scope of PleaseFix, a Vulnerability Class Enabling Zero-Click Attacks Across…

OpenAI’s Browser Could Be Hijacked to Spam Your WhatsApp Contacts

Zenity Labs Exposes the Full Scope of PleaseFix, a Vulnerability Class Enabling Zero-Click Attacks Across Leading Agentic Browsers

Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts