brangberg – Page 581

Researchers Uncover GPT-5 Jailbreak and Zero-Click AI Agent Attacks Exposing Cloud and IoT Systems

Cybersecurity researchers have uncovered a jailbreak technique to bypass ethical guardrails erected by OpenAI in its latest large language model (LLM) GPT-5 and produce illicit instructions.
Generative artificial intelligence (AI) security platform NeuralTrust said it combined a known technique called Echo Chamber with narrative-driven steering to trick the model into producing undesirable

60 malicious Ruby gems downloaded 275,000 times steal credentials

Sixty malicious Ruby gems containing credential-stealing code have been downloaded over 275,000 times since March 2023, targeting developer accounts. […]

Free Wi-Fi Leaves Buses Vulnerable to Remote Hacking

Researchers showed how flaws in a bus’ onboard and remote systems can be exploited by hackers for tracking, control and spying.

The post Free Wi-Fi Leaves Buses Vulnerable to Remote Hacking appeared first on SecurityWeek.

CyberArk and HashiCorp Flaws Enable Remote Vault Takeover Without Credentials

Cybersecurity researchers have discovered over a dozen vulnerabilities in enterprise secure vaults from CyberArk and HashiCorp that, if successfully exploited, can allow remote attackers to crack open corporate identity systems and extract enterprise secrets and tokens from them.
The 14 vulnerabilities, collectively named Vault Fault, affect CyberArk Secrets Manager, Self-Hosted, and

OpenAI to fix GPT-5 issues, double rate limits for paid users after outrage

OpenAI’s CEO, Sam Altman, overpromised on GPT-5, and real-life results are underwhelming, but it looks like a new update is rolling out that might address some of the concerns. […]

WinRAR zero-day flaw exploited by RomCom hackers in phishing attacks

A recently fixed WinRAR vulnerability tracked as CVE-2025-8088 was exploited as a zero-day in phishing attacks to install the RomCom malware. […]

Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise

Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses.

The post Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise appeared first on SecurityWeek.

FTC: older adults lost record $700 million to scammers in 2024

Americans aged 60 and older lost a staggering $700 million to online scams in 2024, marking a sharp rise in fraud targeting seniors, according to the Federal Trade Commission. […]

CodeSecCon 2025: Where Software Security’s Next Chapter Unfolds

Taking place August 12-13, CodeSecCon is the premier virtual event bringing together developers and cybersecurity professionals to revolutionize the way applications are built, secured, and maintained.

The post CodeSecCon 2025: Where Software Security’s Next Chapter Unfolds appeared first on SecurityWeek.

AI Tools Fuel Brazilian Phishing Scam While Efimer Trojan Steals Crypto from 5,000 Victims

Cybersecurity researchers are drawing attention to a new campaign that’s using legitimate generative artificial intelligence (AI)-powered website building tools like DeepSite AI and BlackBox AI to create replica phishing pages mimicking Brazilian government agencies as part of a financially motivated campaign.
The activity involves the creation of lookalike sites imitating Brazil’s State

Author: brangberg