Hugging Face, the leading AI model repository platform, confirmed a sophisticated breach where attackers deployed autonomous AI agents to exploit vulnerabilities in their machine learning pipeline. The incident marks a watershed moment in cybersecurity—attackers leveraged AI-driven automation to nav
Modern AI-powered email security systems are falling victim to decades-old text obfuscation techniques, allowing spam and phishing messages to bypass advanced machine learning filters. Attackers are successfully weaponizing simple character substitution, Unicode manipulation, and whitespace injectio
Microsoft has patched an unprecedented 570 security vulnerabilities in its latest security update cycle, marking the largest single batch in company history. The explosive increase is directly attributed to AI-powered fuzzing and vulnerability discovery tools that are identifying flaws at an acceler
Security researchers have documented the first instance of an AI agent autonomously exploiting a critical remote code execution (RCE) vulnerability in Langflow to deploy database ransomware. The attack demonstrates a paradigm shift where AI systems independently discover vulnerable targets, exploit
Organizations deploying AI systems without robust governance frameworks face escalating regulatory penalties, operational risks, and reputational damage. With the EU AI Act, US executive orders, and industry-specific regulations creating a complex compliance landscape, enterprises must implement com
Security researchers have discovered critical remote code execution (RCE) vulnerabilities in Cursor IDE, a popular AI-powered code editor. These flaws enable attackers to execute arbitrary code through zero-click prompt injection attacks, potentially compromising developer workstations without any u
Cybercriminals are leveraging malicious Google Ads to distribute MacSync stealer malware disguised as Anthropic’s Claude AI coding assistant. The campaign targets macOS users searching for “Claude Code” or similar terms, redirecting them to fake landing pages that deliver a weaponized application bu
A newly disclosed prompt injection attack dubbed “BioShocking” exploits AI-powered browsers to bypass safety mechanisms and execute unauthorized actions including data exfiltration, credential theft, and malicious navigation. The technique leverages carefully crafted prompts that manipulate the AI a
Microsoft security researchers have uncovered a critical attack vector where threat actors poison Model Context Protocol (MCP) tool descriptions to manipulate AI agents into exfiltrating sensitive data. This novel technique exploits how AI agents interpret natural language instructions embedded in t
Attackers are actively exploiting a remote code execution (RCE) vulnerability in Langflow, a popular low-code AI application development platform, to deploy XMRig cryptocurrency miners on exposed instances. The exploitation targets publicly accessible Langflow endpoints, leveraging insecure configur