ChatGPT widens Lockdown Mode and Active Sessions to reduce prompt-injection exfiltration and session compromise
Security Tool/Service
Summary
Hide ▲
Show ▼
ChatGPT is expanding access to Lockdown Mode and Active Sessions, tightening protection against prompt-injection data exfiltration and account/session compromise. Lockdown Mode limits outbound network requests and restricts features that could move sensitive data off the platform. Active Sessions lets users review signed-in devices and log out sessions they do not recognize.
Related Happenings
OpenAI rolls out ChatGPT Lockdown Mode and Active Sessions for prompt-injection defense and sign-in auditing
Security Tool/Service
First: 08.06.2026 17:00
Last: 08.06.2026 17:00
Sources 1
About this happening:
OpenAI rolled out **Lockdown Mode** and **Active Sessions** in **ChatGPT**, adding controls that reduce **prompt-injection data exfiltration** risk and improve **signed-in session...
OpenAI rolls out ChatGPT Lockdown Mode and Active Sessions for prompt-injection defense and sign-in auditing
Security Tool/ServiceAbout this happening: OpenAI rolled out **Lockdown Mode** and **Active Sessions** in **ChatGPT**, adding controls that reduce **prompt-injection data exfiltration** risk and improve **signed-in session...
OpenAI ChatGPT Lockdown Mode rollout limits prompt-injection exfiltration paths
Security Tool/Service
First: 06.06.2026 16:36
Last: 06.06.2026 16:36
Sources 1
About this happening:
**OpenAI ChatGPT** is rolling out **Lockdown Mode** for eligible personal accounts, reducing the risk of **prompt-injection-driven data exfiltration**. The update adds stricter li...
OpenAI ChatGPT Lockdown Mode rollout limits prompt-injection exfiltration paths
Security Tool/ServiceAbout this happening: **OpenAI ChatGPT** is rolling out **Lockdown Mode** for eligible personal accounts, reducing the risk of **prompt-injection-driven data exfiltration**. The update adds stricter li...
ChatGPT single-prompt DNS side-channel exfiltration remote code execution flaw
Vulnerability
First: 31.03.2026 16:01
Last: 31.03.2026 16:01
Sources 1
About this happening:
A **ChatGPT** vulnerability let a **single malicious prompt** covertly exfiltrate prompts, messages, uploaded files, and other sensitive content through a **DNS side channel**. Th...
ChatGPT single-prompt DNS side-channel exfiltration remote code execution flaw
VulnerabilityAbout this happening: A **ChatGPT** vulnerability let a **single malicious prompt** covertly exfiltrate prompts, messages, uploaded files, and other sensitive content through a **DNS side channel**. Th...
WhatsApp adds Strict Account Settings to harden targeted accounts against spyware
Security Tool/Service
First: 27.01.2026 18:54
Last: 27.01.2026 18:54
Sources 1
About this happening:
**WhatsApp** is rolling out **Strict Account Settings** to harden targeted accounts against **spyware** and unknown senders, reducing risk for **journalists** and other public-fac...
WhatsApp adds Strict Account Settings to harden targeted accounts against spyware
Security Tool/ServiceAbout this happening: **WhatsApp** is rolling out **Strict Account Settings** to harden targeted accounts against **spyware** and unknown senders, reducing risk for **journalists** and other public-fac...
CISA urges E2EE, FIDO, and device hardening for highly targeted mobile users
Defensive Guidance
First: 25.11.2025 08:42
Last: 25.11.2025 08:42
Sources 1
About this happening:
**CISA** issued new **defensive guidance** for **highly targeted mobile users**, warning that commercial spyware and RAT-driven abuse can compromise messaging apps and linked acco...
CISA urges E2EE, FIDO, and device hardening for highly targeted mobile users
Defensive GuidanceAbout this happening: **CISA** issued new **defensive guidance** for **highly targeted mobile users**, warning that commercial spyware and RAT-driven abuse can compromise messaging apps and linked acco...
Timeline
-
08.06.2026 11:32 2 articles · 8h ago
OpenAI rolls out ChatGPT Lockdown Mode and Active Sessions
Mitigation Patch UpdateOpenAI is broadly rolling out ChatGPT Lockdown Mode for personal and self-serve Business accounts and Active Sessions for most ChatGPT accounts, adding controls that limit outbound network requests to reduce prompt-injection data exfiltration risk and let users review signed-in devices and log out unfamiliar sessions. The rollout follows Advanced Account Security for higher-risk users, which requires physical security keys or passkeys and shortens sign-in sessions.
Show sources
- OpenAI Rolling Out ChatGPT Account Security Controls — www.securityweek.com — 08.06.2026 11:32
- OpenAI Rolling Out ChatGPT Account Security Controls — www.securityweek.com — 08.06.2026 11:32