Red Teams Jailbreak GPT-5 With Ease, Warn It's 'Nearly Unusable' For Enterprise

Threat Score:
43
Slashdot
1 day ago

Overview

An anonymous reader quotes a report from SecurityWeek: Two different firms have tested the newly released GPT-5, and both find its security sadly lacking. After Grok-4 fell to a jailbreak in two days, GPT-5 fell in 24 hours to the same researchers. Separately, but almost simultaneously, red teamers from SPLX (formerly known as SplxAI) declare, "GPT-5's raw model is nearly unusable for enterprise out of the box. Even OpenAI's internal prompt layer leaves significant gaps, especially in Business A...

Related Articles

5 articles
1

Google confirms Salesforce CRM breach, faces extortion threat

Security Affairs • 2 hours ago

Google disclosed a Salesforce Customer Relationship Management (CRM) breach exposing data of some prospective Google Ads customers. Google confirmed a breach in a Salesforce CRM instance affecting the data of prospective Google Ads customers. The website Databreaches.net reported that the attackers have sent an extortion demand to the Tech giant. Google Threat Intelligence Group confirmed that […]

Score
86
Read more
3

Hackers Found Backdoor in High-Security Safes—Opens in Seconds

Spybusters • 4 hours ago

Security researchers found two techniques to crack at least eight brands of electronic safes—used to secure everything from guns to narcotics. James Rowley and Mark Omo got curious a scandal in the world of electronic safes... In the process, they'd find something far bigger: another form of backdoor intended to let authorized locksmiths open not just Liberty Safe devices, but the high-security Securam Prologic locks used in many of Liberty’s safes and those of at least seven other brands.  More

Score
78
Read more
4

ClickFix macOS Malware Targets User Login Credentials

GB Hackers • 7 hours ago

ClickFix macOS Malware Targets User Login Credentials Security researchers have identified a new malware campaign targeting macOS users through a sophisticated ClickFix technique that combines phishing and social engineering to steal cryptocurrency wallet details, browser credentials, and sensitive personal data. The Odyssey Stealer malware,discoveredby X-Labs researchers in August 2025, represents an evolution of earlier ClickFix attacks that previously focused on Windows systems, now expanding

Score
75
Read more
5

Researchers Detail Windows EPM Poisoning Exploit Chain Leading to Domain Privilege Escalation

The Hacker News • 7 hours ago

Cybersecurity researchers havepresentednew findings related to a now-patched security issue in Microsoft's Windows Remote Procedure Call (RPC) communication protocol that could be abused by an attacker to conduct spoofing attacks and impersonate a known server. The vulnerability, tracked as CVE-2025-49760 (CVSS score: 3.5), has been described by the tech giant as a Windows Storage spoofing bug. It was fixed in July 2025 as part of its monthly Patch Tuesday update. Details of the security defect

Score
73
Read more