Find notable cyber news and cases, enriched with sources, timelines, and signals.
Home Watchlists Beta Browse News Feed Stats About Contact

OpenAI rolls out ChatGPT Lockdown Mode and Active Sessions for prompt-injection defense and sign-in auditing

Security Tool/Service
First reported
Last updated
Happening score
H score 10
1 unique sources, 1 articles

Summary

Hide ▲

OpenAI rolled out Lockdown Mode and Active Sessions in ChatGPT, adding controls that reduce prompt-injection data exfiltration risk and improve signed-in session auditing. The new controls reach beyond awareness messaging by changing how the service can connect to the web and external services and by exposing account sign-in visibility. The rollout began reaching personal and self-serve business accounts in early June 2026 after first being offered to enterprise plans in February.

Related Happenings

ChatGPT widens Lockdown Mode and Active Sessions to reduce prompt-injection exfiltration and session compromise

Security Tool/Service
First: 08.06.2026 11:32 Last: 08.06.2026 11:32 Sources 1

About this happening: **ChatGPT** is expanding access to **Lockdown Mode** and **Active Sessions**, tightening protection against **prompt-injection data exfiltration** and **account/session compromise...

Open Happening

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...

Open Happening

NCSC passkey login guidance shift

Public Sector Action
First: 23.04.2026 11:45 Last: 23.04.2026 11:45 Sources 1

About this happening: The **UK National Cyber Security Centre (NCSC)** has backed **passkeys** as the first choice of login and stopped recommending **passwords** except where passkeys are unavailable,...

Open Happening

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...

Open Happening

OpenAI Safety Bug Bounty launch

Commercial Activity
First: 26.03.2026 14:20 Last: 26.03.2026 14:20 Sources 1

About this happening: **OpenAI** launched the **Safety Bug Bounty** on **Bugcrowd**, expanding researcher coverage for **AI abuse** and **safety risks** across its products. The new program complements...

Open Happening

Timeline

  1. 08.06.2026 17:00 2 articles · 3h ago

    OpenAI adds Lockdown Mode and Active Sessions to ChatGPT

    Initial Disclosure

    OpenAI added two ChatGPT security controls: Lockdown Mode limits how far ChatGPT can reach into the web and external services to reduce prompt-injection data theft, and Active Sessions lets users review account sign-ins with device or browser details, approximate location, sign-in time, and first-party app use. The controls began reaching personal and self-serve business accounts in early June after first being offered to enterprise plans in February, while Lockdown Mode also disables live connector access and write actions and is unavailable alongside Developer Mode or on some SSO-managed accounts.

    Show sources
    Open in new tab