ChatGPT’s Memory Feature Supercharges Prompt Injection
The “ZombieAgent” exploit makes use of ChatGPT’s long-term memory and advanced capabilities.
The “ZombieAgent” exploit makes use of ChatGPT’s long-term memory and advanced capabilities.
Related
SolarWinds Fixes Four Critical Web Help Desk Flaws With Unauthenticated RCE and Auth Bypass
SolarWinds has released security updates to address multiple security vulnerabilities impacting SolarWinds Web Help Desk, including four critical vulnerabilities that could result in authentication bypass and remote code execution (RCE). The list of vulnerabilities is as follows – CVE-2025-40536 (CVSS score: 8.1) – A security control bypass vulnerability that could allow an unauthenticated
Android 17 Blocks Non-Accessibility Apps from Accessibility API to Prevent Malware Abuse
Google is testing a new security feature as part of Android Advanced Protection Mode (AAPM) that prevents certain kinds of apps from using the accessibility services API. The change, incorporated in Android 17 Beta 2, was first reported by Android Authority last week. AAPM was introduced by Google in Android 16, released last year. When…
Critical n8n Flaw (CVSS 9.9) Enables Arbitrary Code Execution Across Thousands of Instances
A critical security vulnerability has been disclosed in the n8n workflow automation platform that, if successfully exploited, could result in arbitrary code execution under certain circumstances. The vulnerability, tracked as CVE-2025-68613, carries a CVSS score of 9.9 out of a maximum of 10.0. The package has about 57,000 weekly downloads, according to statistics on npm….
MITRE EMB3D for OT & ICS Threat Modeling Takes Flight
Manufacturers and infrastructure providers are gaining options to satisfy regulations and boost cyber safety for embedded and industrial control systems, as EMB3D, STRIDE, and ATT&CK for ICS gain traction.
Winning Against AI-Based Attacks Requires a Combined Defensive Approach
If there’s a constant in cybersecurity, it’s that adversaries are always innovating. The rise of offensive AI is transforming attack strategies and making them harder to detect. Google’s Threat Intelligence Group, recently reported on adversaries using Large Language Models (LLMs) to both conceal code and generate malicious scripts on the fly, letting malware shape-shift in…
Lazarus Group Deploys Marstech1 JavaScript Implant in Targeted Developer Attacks
The North Korean threat actor known as the Lazarus Group has been linked to a previously undocumented JavaScript implant named Marstech1 as part of limited targeted attacks against developers. The active operation has been dubbed Marstech Mayhem by SecurityScorecard, with the malware delivered by means of an open-source repository hosted on GitHub that’s associated with…