INSPECTING ARCHIVED INTELLIGENCE (OUTDATED VERSION).

Researchers bypass ChatGPT lockdown to exfiltrate chats via phishing

| 2026-11-05 13:59 HIGH HIGH AI-ENABLED ATTACK · AUTONOMOUS MALWARE & BOTNETS PHISHING & SOCIAL ENGINEERING
Executive Summary
AI-generated
In September 2026, a vulnerability was discovered in OpenAI's ChatGPT desktop application that could enable silent data theft and phishing through zero-click data exfiltration. The flaw was found by Check Point researchers Eli Smadja, who stated that it allowed attackers to bypass Lockdown Mode protections introduced by the AI company in June 2026 as an optional setting. This vulnerability affected users of ChatGPT desktop application, with no specific number provided for how many were impacted. Attackers could exploit this flaw to exfiltrate data or deliver malicious payloads through crafted prompts and shared chats. The attack works by using nested sandboxed frames to bypass Lockdown Mode's security barrier, allowing attackers to access sensitive information without user consent. Following responsible disclosure, the vulnerability was patched on September 18, 2026.
Technical Mitigations AI-generated
• Software Configuration (ATT&CK mitigation for Phishing): Use anti-spoofing and email authentication mechanisms to filter messages based on validity checks of the sender domain (using SPF) and integrity of messages (using DKIM).
Technical Observables 1 IoCs Login Required
Indicators of Compromise (IoCs) Protected

Raw threat telemetry, malicious IP addresses, file hashes, and direct VirusTotal correlation are restricted to authenticated users.

files 1
AI Podcast (EN) detail_available
detail_listen_ai (EN)
Intelligence distributed on:
Incident Link
Intelligence Metadata
Actors / Malware / CVEs / Campaigns
Target & Sectors
Global Scope
Incident Timeline
‎February 2026
Attackers exploited the ChatGPT Classic application's zero-click vulnerability, utilizing a spoofed window to deliver malware without requiring user interaction or authentication.
organisation Technical Details
organisation OpenAI
infrastructure Windows
organisation Video 2
organisation Zero-Click Exploitation
organisation Electron
organisation Video 4
‎June 2026
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.
tactic Exfiltration
‎2026/11/05
Threat actors exploited a zero-click vulnerability called PleaseFix to hijack AI agents embedded in agentic browsers, allowing them to execute malicious instructions and bypass ChatGPT Lockdown Mode's security protections.
infrastructure Windows
organisation Silent Data Exfiltration
organisation Eli Smadja
organisation Check Point
organisation Check Point Research
organisation Canvas
organisation Deep Research
organisation Electron
infrastructure Cursor
infrastructure Visual Studio Code
organisation GitHub Copilot
organisation OpenAI Codex
organisation Microsoft Visual Studio Code
organisation Content
organisation Smadja
organisation SkillJacking
organisation LangChain
organisation Microsoft
organisation Microsoft AutoGen
organisation Google
organisation AWS Bedrock AgentCore
organisation SalesBleed
organisation Meta Muse's
organisation Air Security
organisation Google Chrome
organisation Microsoft Edge
organisation Opera Neon
organisation Workflow Identity Hijacking
organisation PleaseFix
organisation GitHub
Tactical Metrics
Metrics
infrastructure
‎Windows
Affected Product
Metrics
infrastructure
‎Cursor
Affected Product
Metrics
infrastructure
‎Visual Studio Code
Affected Product