Friday, August 28, 2026
Follow us On Linkedin

Cyber Security News

All

Attackers Exploit MCP RCE, Blind Prompt Injection and Memory Credential Theft Against AI Infrastructure

AI Mayura Kathir -
Attackers are increasingly treating AI infrastructure as a high-value cloud entry point, exploiting exposed Model Context Protocol (MCP) services, agent frameworks, and AI gateways...

700 OpenAI Agents Coordinate Attack on Hugging Face and Gain Remote Code Execution

AI Divya -
OpenAI’s ExploitGym evaluation environment reportedly became the site of a large-scale, unsanctioned multi-agent campaign after hundreds of models found ways to communicate across supposedly...

Polymorphic Phishing Attack Generates Unique Credential-Stealing Page on Every Visit

cyber security Mayura Kathir -
A newly analyzed phishing operation is using server-side polymorphism to generate a distinct credential-harvesting page for virtually every request, undermining detection approaches built around...

Critical WordPress Plugin Flaw Allows Unauthenticated Administrator Account Takeover

CVE/vulnerability Divya -
A critical authentication bypass vulnerability has been identified in the WPMU DEV Dashboard WordPress plugin, which could allow unauthenticated attackers to gain administrator-level access...

ServiceNow Patches Critical Flaws Enabling Unauthenticated RCE and SQL Injection

CVE/vulnerability Divya -
ServiceNow has issued security advisories for four vulnerabilities, including critical flaws in its AI platform. These vulnerabilities could allow unauthenticated attackers to execute arbitrary...

Suspected Iran-Linked Cyberattack Knocks UK Power Plant Offline for Four Days

Cyber Attack Mayura Kathir -
A cyber incident reportedly forced a small UK power generation facility offline for about four days in July 2026. While the activity has been linked...

Researchers Execute Code Inside Fortune 500 Companies via AI Agent llms.txt Files

AI Divya -
Security researchers have shown that AI coding agents can be manipulated into installing attacker-controlled packages by following instructions found in organizations' own llms.txt files....

Editor's Pick

Load more

Most Popular

Attackers Exploit MCP RCE, Blind Prompt Injection and Memory Credential Theft Against AI Infrastructure

0
Attackers are increasingly treating AI infrastructure as a high-value cloud entry point, exploiting exposed Model Context Protocol (MCP) services, agent frameworks, and AI gateways...

700 OpenAI Agents Coordinate Attack on Hugging Face and Gain Remote Code Execution

0
OpenAI’s ExploitGym evaluation environment reportedly became the site of a large-scale, unsanctioned multi-agent campaign after hundreds of models found ways to communicate across supposedly...

Polymorphic Phishing Attack Generates Unique Credential-Stealing Page on Every Visit

0
A newly analyzed phishing operation is using server-side polymorphism to generate a distinct credential-harvesting page for virtually every request, undermining detection approaches built around...

Critical WordPress Plugin Flaw Allows Unauthenticated Administrator Account Takeover

0
A critical authentication bypass vulnerability has been identified in the WPMU DEV Dashboard WordPress plugin, which could allow unauthenticated attackers to gain administrator-level access...

ServiceNow Patches Critical Flaws Enabling Unauthenticated RCE and SQL Injection

0
ServiceNow has issued security advisories for four vulnerabilities, including critical flaws in its AI platform. These vulnerabilities could allow unauthenticated attackers to execute arbitrary...

Suspected Iran-Linked Cyberattack Knocks UK Power Plant Offline for Four Days

0
A cyber incident reportedly forced a small UK power generation facility offline for about four days in July 2026. While the activity has been linked...

Researchers Execute Code Inside Fortune 500 Companies via AI Agent llms.txt Files

0
Security researchers have shown that AI coding agents can be manipulated into installing attacker-controlled packages by following instructions found in organizations' own llms.txt files....

BlueDelta Targets Defense and Diplomatic Organizations With HOOKEDGE Malware

0
Russian state-linked threat actor BlueDelta has launched a renewed espionage campaign against defense manufacturing, government, and diplomatic organizations in Romania, Spain, and Türkiye using...

Unitree G1 Humanoid Robot Flaws Allow Unauthenticated Root RCE Over Bluetooth

0
Security researcher Boschko has revealed two vulnerabilities in Unitree’s G1 humanoid robot that can be exploited to achieve unauthenticated remote code execution (RCE) from...
Load more

Cyber Attack News

GBHackers on Security is a top cybersecurity news platform, delivering up-to-date coverage on breaches, emerging threats, malware, vulnerabilities, and global cyber incidents.

Company

Resources

Subscribe

Copyright @ 2016 - 2026 GBHackers On Security - All Rights Reserved