A previously unknown vulnerability in OpenAI ChatGPT allowed sensitive conversation data to be exfiltrated without user knowledge or consent, according to new findings from Check Point. "A single malicious prompt could turn an otherwise ordinary conversation into a covert exfiltration channel, leaki
โกKey InsightsAI analyzingโฆ
I
info@thehackernews.com (The Hacker News)
๐ก
Tags:#security#the-hacker-news
Found this useful? Share it!
Read the Full Story
Continue reading on The Hacker News
Related Stories

๐Security
Geopolitics, AI, and Cybersecurity: Insights From RSAC 2026
about 14 hours ago

๐Security
Not Toying Around: Hasbro Attack May Take 'Weeks' to Remediate
about 15 hours ago

๐Security
Hackers Exploit CVE-2025-55182 to Breach 766 Next.js Hosts, Steal Credentials
about 16 hours ago

๐Security
Security Bosses Are All-In on AI. Here's Why
about 16 hours ago
