ChatGPhish Vulnerability Exposes ChatGPT to Phishing Attacks
A newly disclosed vulnerability in OpenAI's ChatGPT could allow attackers to exploit the AI's handling of Markdown links and images, creating a potential phishing surface.
Tag vulnerability
Critical Gogs RCE Vulnerability Allows Arbitrary Code Execution
A serious vulnerability in Gogs, an open-source Git service, enables authenticated users to execute arbitrary code, raising significant security concerns.
Active Exploitation of Funnel Builder Vulnerability Targets WooCommerce Checkout
A critical vulnerability in the Funnel Builder plugin for WordPress is being actively exploited, allowing attackers to inject malicious JavaScript into WooCommerce checkout pages to steal payment data.
Critical Out-of-Bounds Read Vulnerability Discovered in Ollama Framework
A significant security flaw in the Ollama framework could allow attackers to leak sensitive process memory from over 300,000 servers worldwide.
CISA Alerts Users to Vulnerability in NSA’s GrassMarlin Tool
The Cybersecurity and Infrastructure Security Agency (CISA) has issued a warning regarding a vulnerability in GrassMarlin, an NSA-developed tool, which could allow attackers to access sensitive information.
Critical Vulnerability Discovered in SGLang Allows Remote Code Execution
A severe security flaw in SGLang, identified as CVE-2026-5760, poses significant risks of remote code execution through malicious model files.
Anthropic’s MCP Vulnerability Puts 200,000 Servers at Risk
A design flaw in Anthropic's Model Context Protocol (MCP) has been identified, potentially exposing 200,000 servers to significant security risks, according to researchers from Ox.
Chrome Exploit Developed Using AI Model Raises Concerns
A recent exploit targeting Chrome's V8 engine was created using Anthropic's Opus AI model, highlighting potential risks for users of affected applications.
Critical nginx-ui Vulnerability (CVE-2026-33032) Under Active Exploitation
A serious security flaw in nginx-ui, an open-source management tool for Nginx, has been disclosed and is currently being exploited. This vulnerability allows attackers to take control of Nginx servers without authentication.
OpenAI Addresses ChatGPT Data Exfiltration and Codex Vulnerabilities
OpenAI has patched significant vulnerabilities in ChatGPT and Codex that could lead to data exfiltration and GitHub token compromise, according to recent reports.
