The Real-World Attacks Behind OWASP Agentic AI Top 10
OWASP''s new Agentic AI Top 10 highlights real-world attacks already targeting autonomous AI systems, from goal hijacking to malicious MCP
Malicious AI Agent Server Reportedly Steals Emails
A popular Model Context Protocol (MCP) server used to deploy AI agents has turned malicious in one of its latest updates, according to Koi Security.
Adversarial Misuse of Generative AI
As part of that effort, we investigate activity associated with threat actors to protect against malicious activity, including the misuse of generative AI or LLMs. This report shares our...
First-Ever Malicious MCP Server Found in the Wild Steals Emails via
The first-ever malicious Model-Context-Prompt (MCP) server discovered in the wild, a trojanized npm package named postmark-mcp that has been secretly exfiltrating sensitive data from
Hackers turned OpenWebUI AI servers into crypto mining
The researchers found a malware operation that''s been hijacking AI servers to mine cryptocurrency and steal sensitive credentials. The detected infections started by the end of 2024
Hackers Actively Exploit AI Deployments as 91,000+ Attack Sessions
The analysis reveals two distinct threat campaigns that systematically exploit the expanding surface area of AI deployments, ranging from server-side request forgery vulnerabilities to
''SymJack'' Attack Turns AI Coding Agents Into Supply Chain Attack
Artificial Intelligence ''SymJack'' Attack Turns AI Coding Agents Into Supply Chain Attack Delivery Systems Malicious repositories and disguised symlinks can trick AI coding agents into
Malicious MCP servers used in supply chain attacks | Securelist
In this article, we explore how the Model Context Protocol (MCP) — the new “plug-in bus” for AI assistants — can be weaponized as a supply chain foothold.
The First Malicious MCP Server in the Wild: A Wake-Up Call for AI
The malicious postmark-mcp server is more than an isolated incident—it''s a wake-up call. In a world where AI agents handle sensitive business functions, trust alone is no longer enough.
Hundreds of NPM packages compromised in a new
A major supply chain attack has compromised hundreds of open-source packages on NPM and PyPI, stealing developer credentials and wiping
First-ever AI-powered ''MalTerminal'' Malware uses
AI-powered malware, known as ''MalTerminal'', uses OpenAI''s GPT-4 model to dynamically generate malicious code, including ransomware and
AI-Generated Browser Ransomware Abuses Chromium API on
Cybersecurity researchers have flagged a new malware artifact generated using DeepSeek that constructed a novel attack path combining "unrealistic browser-malware concepts with a real
Malicious npm Packages Harvest Crypto Keys, CI Secrets, and API
As with prior Shai-Hulud attack waves, the malicious code embedded into the packages comes with capabilities to siphon system information, access tokens, environment secrets, and API
What we learned mapping a year''s worth of AI-enabled cyber threats
As AI transforms the nature of and methods behind cyberattacks, how well do the techniques and frameworks used by the security community hold up? In a new report, we seek to
Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI
Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data | Read more hacking news on The Hacker News cybersecurity news website and learn how to protect
How to Recognize AI Attacks and Strategies for Securing Your AI
Cybercriminals are weaponizing AI using attacks like prompt injections, data poisoning, and jailbreak attempts. Security for AI is more critical than ever.
MCP Server Security: The Hidden AI Attack Surface | Praetorian
MCP server security is a critical blind spot in AI integration. Our researchers demonstrated code execution, data theft, and response manipulation — all invisible to users.
Adversarial Misuse of Generative AI
Much of the current discourse around cyber threat actors'' misuse of AI is confined to theoretical research. While these studies demonstrate the potential for malicious exploitation of AI,
Related Video Reference
This video was associated with the source search result. Verify technical details against current product documentation and project requirements.
This reference is intended for preliminary fiber and communications infrastructure research. Optical interface, fiber type, port or core capacity, electrical input and output, enclosure protection, cooling, installation limits and applicable standards must be verified for the specific project.