Researchers from Zenity have found multiple ways to inject rogue prompts into agents from mainstream vendors to extract ...

Researchers bypass GPT-5 guardrails using narrative jailbreaks, exposing AI agents to zero-click data theft risks.

Attackers could exploit widely deployed AI technologies for data theft and manipulation, experts from Zenity Labs found.

The industry’s biggest annual get together offers CISOs insights into security researcher’s latest findings. From cloud ...

Cybersecurity researchers have demonstrated a jailbreak of OpenAI’s latest large language model, GPT-5, less than a day after ...

Copilot, Gemini, and Salesforce's Einstein, were also found to have security loopholes that businesses should be aware of. The post AI Agents Like ChatGPT Are Vulnerable to Hacking, Security Firm ...

The Israeli cybersecurity company Zenity revealed how one could take control of a ChatGPT account and extract sensitive information without the user clicking any link.

This tool adds a highly trained virtual analyst to your security team in educational environments where IT personnel and ...

A concerning zero-day vulnerability in WinRAR (CVE-2025-8088) allows hackers to hijack your PC. Users are advised to update ...

CrushFTP is warning that threat actors are actively exploiting a zero-day vulnerability tracked as CVE-2025-54309, which allows attackers to gain administrative access via the web interface on ...

Apple has released security updates to address a high-severity vulnerability that has been exploited in zero-day attacks targeting Google Chrome users.