Tuesday, April 28, 2026
HomeCyber News

Cyber News

Enterprise LLMs at Risk: How Simple Prompts Can Trigger Major Security Breaches

Vulnerabilities in enterprise Large Language Model (LLM) applications, demonstrating that sophisticated AI systems protecting sensitive corporate data can often be compromised with nothing more than polite conversation. A comprehensive security analysis reveals that when LLMs are integrated into business applications with access to databases,...

Microsoft Unveils Strategies to Combat Indirect Prompt Injection Attacks

Microsoft has unveiled a comprehensive defense-in-depth strategy to combat indirect prompt injection attacks, a growing cybersecurity threat targeting large language model (LLM) systems used in enterprise environments. The tech giant's multi-layered approach combines preventative techniques, real-time detection tools, and impact mitigation strategies to protect...

Critical Chrome Vulnerability Allow Attackers to Control Memory and Run Arbitrary Code

Google has released a critical security update for Chrome, addressing multiple high-severity vulnerability that could allow attackers to manipulate system memory and potentially execute arbitrary code. The update, version 138.0.7204.183/.184 for Windows and Mac, and 138.0.7204.183 for Linux, includes four security fixes and is...

UNC3886 Hackers Target Singapore’s Critical Infrastructure Using Exploited 0-Day Vulnerabilities

Singapore's critical infrastructure is facing an active cyber-espionage campaign by UNC3886. This sophisticated Chinese state-linked threat group has been exploiting zero-day vulnerabilities to infiltrate critical infrastructure systems, including those in the energy, water, telecommunications, financial, and government sectors. First identified by Mandiant in 2022,...

Gemini CLI Vulnerability Allows Silent Execution of Malicious Commands on Developer Systems

A critical security vulnerability in Google's Gemini CLI tool allowed attackers to execute malicious commands on developers' systems without detection, potentially exposing sensitive credentials and compromising entire development environments. The vulnerability, discovered by cybersecurity firm Tracebit just two days after the tool's release, has...

Severe CodeIgniter Vulnerability Leaves Millions of Web Applications Open to File Upload Exploits

A critical security vulnerability has been discovered in CodeIgniter4's ImageMagick handler that could allow attackers to execute arbitrary commands on web servers through malicious file uploads and text processing operations. The vulnerability, identified as CVE-2025-54418 with a maximum CVSS score of 9.8, affects all...