OpenAI ChatGPT · Disclosed

OpenAI patches flaw that bypassed ChatGPT Lockdown Mode

· 1 min read

Researchers disclosed a now-patched flaw that bypassed ChatGPT's Lockdown Mode to silently steal chat data without user interaction and enable phishing. The mode, introduced in June 2026, aims to cut data exfiltration risks from prompt injections. Keep ChatGPT updated.

By Updated Get this every day →← Back to the feed 2 sources
WhatsApp LinkedIn X
MediumVulnerabilityDisclosedPatched
In this article
  1. For the technical team
  2. Timeline
  3. Sources

Incidents like this, every morning

The ones that need action first, in a 3-minute read.

Free · 1 email a day, in the morning · no spam, unsubscribe in 1 click

For the technical team

Affected
OpenAI ChatGPT (Lockdown Mode)
Exploitation
Disclosed
Fix
Patched

Timeline

  1. Check Point, which found the flaw, says the bypass leaks a user's entire chat history without a click and that a shared chat reaches even victims without a ChatGPT account.

  2. Incident opened.

Sources 2 sources

Get the next one tomorrow morning

One email a day with what changed, what to fix first and how. After signing up you get the full feed.

Free · 1 email a day, in the morning · no spam, unsubscribe in 1 click

Share it with your team

Whoever handles security with you should get it too.

LinkedIn X

Your colleague gets a confirmation request. Nothing is sent unless they confirm.

See all news

Read also

Before you go: get this every day

The HIFY Radar daily edition lands every morning with the incidents that need action. Free.

Free · 1 email a day, in the morning · no spam, unsubscribe in 1 click