CVE-2026-110662

The MxChat – AI Chatbot & Content Generation for WordPress plugin for WordPress is vulnerable to Stored DOM-Based Cross-Site Scripting via the 'feedback' parameter in all versions up to, and including, 3.2.25 due to insufficient input sanitization and output escaping. This makes it possible for...

CVE-2026-110662

The MxChat WordPress plugin (all versions up to and including 3.2.25 ) is vulnerable to Stored DOM-Based Cross-Site Scripting (XSS) . The root cause is insufficient input sanitization and output escaping of the 'feedback' parameter. An unauthenticated attacker can inject arbitrary web scripts by ...

EUVD-2026-111736

The MxChat – AI Chatbot & Content Generation for WordPress plugin for WordPress is vulnerable to Stored DOM-Based Cross-Site Scripting via the 'feedback' parameter in all versions up to, and including, 3.2.25 due to insufficient input sanitization and output escaping. This makes it possible for...

PT-2026-127874

The MxChat – AI Chatbot & Content Generation for WordPress plugin for WordPress is vulnerable to Stored DOM-Based Cross-Site Scripting via the 'feedback' parameter in all versions up to, and including, 3.2.25 due to insufficient input sanitization and output escaping. This makes it possible for...

TrainShield: Targeted Awareness for Cybersecurity Training

In recent years, cybersecurity threats have increasingly exploited human behaviour rather than purely technical vulnerabilities, exposing the limits of traditional awareness programmes delivered outside real-world contexts. To bridge this gap, we introduce TrainShield, an interaction paradigm for...

CVE-2026-13005: Improper Neutralization of Input During Web Page Generation

The MxChat – AI Chatbot & Content Generation for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting via admin settings in all versions up to, and including, 3.2.10 due to insufficient input sanitization and output escaping. This makes it possible for authenticated...

MAI-2024-0019

Large Language Models LLMs are prone to a specific vulnerability where they exhibit a bias towards authoritative sources. This allows malicious actors to circumvent built-in safety mechanisms by crafting prompts that include fabricated citations resembling credible sources, such as academic paper...

CVE-2026-25391

Missing Authorization vulnerability in WP Grids WP Wand ai-content-generation allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects WP Wand: from n/a through = 1.3.07...

CVE-2026-25391

Missing Authorization vulnerability in WP Grids WP Wand ai-content-generation allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects WP Wand: from n/a through = 1.3.07...

CVE-2026-25391

CVE-2026-25391 : The WP Wand plugin’s AI content-generation feature (WP Wand ai-content-generation) is affected by a Missing Authorization vulnerability in versions up to and including 1.3.07. The issue allows exploitation through incorrectly configured access control security levels (Broken Acce...

CVE-2026-25391 WordPress WP Wand plugin <= 1.3.07 - Broken Access Control vulnerability

Missing Authorization vulnerability in WP Grids WP Wand ai-content-generation allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects WP Wand: from n/a through = 1.3.07...

CVE-2026-25391

Missing Authorization vulnerability in WP Grids WP Wand ai-content-generation allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects WP Wand: from n/a through = 1.3.07...

CVE-2026-25391: Missing Authorization

Missing Authorization vulnerability in WP Grids WP Wand ai-content-generation allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects WP Wand: from n/a through = 1.3.07...

PT-2026-20724

Missing Authorization vulnerability in WP Grids WP Wand ai-content-generation allows Exploiting Incorrectly Configured Access Control Security Levels.This issue affects WP Wand: from n/a through = 1.3.07...

EUVD-2025-5986

Malicious code in bioql PyPI...

EUVD-2025-6118

Malicious code in bioql PyPI...

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 calle...

Phare: a Safety Probe for Large Language Models

Ensuring the safety of large language models LLMs is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to probe and evaluate LLM behavior across three critical...

Claude AI Exploited to Operate 100+ Fake Political Personas in Global Influence Campaign

Artificial intelligence AI company Anthropic has revealed that unknown threat actors leveraged its Claude chatbot for an "influence-as-a-service" operation to engage with authentic accounts across Facebook and X. The sophisticated activity, branded as financially-motivated, is said to have used i...

CVE-2025-22623

CVE-2025-22623 affects the WordPress plugin Ad Inserter – Ad Manager and AdSense Ads (version 2.8.0 and earlier). The vulnerability arises from the web application generating content without validating the origin of untrusted data in myapp/includes/dst/dst.php, enabling a reflected cross-site scr...