ThreatCluster

HackedGPT: Seven Vulnerabilities Found in GPT-4o and GPT-5

First seen 2 Dec 2025, 18:33 UTC •CybersecuritynewsCyberpress •83% similarity •12

Article Content

Browse articles
ThreatCluster

Seven new vulnerabilities have been identified in the AI models GPT-4o and GPT-5, potentially allowing for zero-day exploits. These vulnerabilities could impact various applications utilizing these models, raising significant security concerns within the cybersecurity community. The details surrounding the vulnerabilities and their implications are currently under analysis.

ThreatCluster AI

Extracted Entities

1 / 2

Community

Browse all →

Tracked Entities in This Story

GPT-4o Data Breach Malware Gpt-5