News
threat-intel Unpatchable Hardware Flaws in Older iPhones Allow Attackers to Steal Crypto Wallet Recovery Phrases - GBHackers threat-intel New ChatGPT Phishing Kit Uses Rotating WordPress Websites to Steal Payment Details and OTPs - GBHackers cybersecurity Hackers Compromise Ukraine and Russia’s Emergency Alert Apps to Spread Fake Nuclear Warnings - CyberPress cybersecurity Malicious Claude Code Extension Served in Cursor Supply Chain Attack - SecurityWeek cybersecurity Synology warns of C3RB3R ransomware attacks targeting NAS devices - BleepingComputer threat-intel Hackers Target Emergency Alert Apps in Ukraine and Russia, Sending Fake Nuclear Attack Warnings - GBHackers cybersecurity Attackers Pose as IT Support on Microsoft Teams, Abuse AD CS to Steal Company Data - The Hacker News threat-intel Hackers Target Supermarket Refrigeration Systems Across Sweden, Raising Freezer Temperatures to 55°C - GBHackers cybersecurity Hackers Use Fake ChatGPT Plus Billing Emails to Steal Credit Card Details and OTP Codes - CyberPress cybersecurity Hackers Target Supermarket Refrigeration Systems in Sweden, Raising Temperatures to 50°C - CyberPress threat-intel Additional Ivanti Connect Secure zero-days exploited in the wild (CVE-2026-111357, CVE-2026-118527) - Rapid7 Emergent Threat Response cybersecurity My Journey to the Center of America’s Political Spam Text Hell - Wired Security threat-intel Researchers Discover High-Severity ChatGPT Flaw That Exposed Private Conversations to Attackers - GBHackers threat-intel Hackers Weaponize Open-Source CyberStrikeAI Framework to Launch AI-Powered Network Intrusions - GBHackers cybersecurity Government Linux Servers Targeted With SysGoRAT and Suspected AI-Generated Scripts - The Hacker News
1 / 15
All news ›
Cybersecurity

OpenAI Fixes High-Severity ChatGPT Flaw That Exposed Private Conversations to Attackers

CyberPress ·

OpenAI has fixed a high-severity ChatGPT vulnerability that let attackers expose private conversations by luring signed-in users into a malicious shared conversation. Researcher Mukul Goyal disclosed the findings on October 28, reporting that OpenAI resolved the issue on October 26 and classified it as P1. The exploit combined public conversation sharing, HTML Preview, the MathLive […] The post OpenAI Fixes High-Severity ChatGPT Flaw That Exposed Private Conversations to Attackers appeared first on Cyber Security News .

Continue on CyberPress ↗ ‹ All news Get the newsletter

The summary and image come from CyberPress; the image is shown from their website.