In 2025, AI has evolved from being a tool that merely enhances the efficiency of attacks to becoming an integral component embedded within the execution phase of cyber operations. In the future, AI may even emerge as a pivotal enabler for attack activities. During the initial attack phase, AI technology has...
Tag: AI
Protecting AI Security: 2025 Hot Security Incident
GitHub MCP Cross-Repository Data Leak Vulnerability In May 2025, Invariant disclosed a critical vulnerability in GitHub's Machine Collaboration Protocol (MCP), where attackers embedded malicious commands within public repository Issues to hijack developers' locally running AI Agents. When an AI Agent was triggered to read and "assist" in processing the Issue,...
AI-Empowered Cybersecurity: Key Events and Emerging Trends in 2025
In September 2025, Anthropic disclosed a groundbreaking incident—the world’s first autonomous AI-driven cyberattack. This event, documented as the first large-scale cyber offensive primarily executed by AI with minimal human intervention, underscored the immense threat posed by AI agents in malicious applications. The attackers posed as representatives of a legitimate cybersecurity firm...
AI-PTS: Breaking Traditional Barriers, Revolutionizing Penetration Testing
AI Penetration Testing System (AI-PTS) Leveraging AI to empower penetration testing, the AI-PTS integrates AI technology with traditional penetration testing methods. It delivers an AI+ defense system tailored for real-world attack scenarios. The AI-PTS is designed to help security professionals conduct non-destructive security assessments for networks, systems, and applications, significantly...
Building a Full-Lifecycle Defense System for Large Language Model Security
Santa Clara, Calif. Oct 2, 2025 – Recently, NSFOCUS held the AI New Product Launch in Beijing, comprehensively showcasing the company's latest technological achievements and practical experience in AI security. With large language model security protection as the core topic, the launch systematically introduced NSFOCUS's concept and practices in strategy planning,...
Prompt Injection: An Analysis of Recent LLM Security Incidents
Overview With the widespread application of LLM technology, data leakage incidents caused by prompt word injections are increasing. Many emerging attack methods, such as inducing AI models to execute malicious instructions through prompt words, and even rendering sensitive information into pictures to evade traditional detection, are posing serious challenges to...
