TL;DR: A comprehensive look at the AI security landscape in 2025, from critical LLM vulnerabilities and shadow AI risks to agentic AI threats, new OWASP frameworks, and what enterprise security leaders should prioritize in 2026. — AI security as a discipline…
AI Security News: Jailbreaks, Agent Exploits, and MCP Supply Chain Flaws
Week ending December 8, 2025 This week’s news spans novel jailbreaking techniques, browser agent vulnerabilities, and emerging supply chain risks in the protocols connecting AI systems to the outside world. Perplexity Tackles Browser Agent Security with BrowseSafe AI browser agents can…
ChatGPT Turns 3: What Have We Learned?
OpenAI launched ChatGPT three years ago. Since then, security researchers have discovered vulnerabilities in plugins, memory features, and autonomous agents that challenge traditional security models.
Agentic AI is Already Running the Kill Chain – Inside Anthropic’s Latest Threat Report
Anthropic’s latest threat report documents the first confirmed case of an agentic AI executing the majority of a cyber-espionage kill chain through MCP servers and standard tools, underscoring the need for real-time visibility, control, and enforcement across all AI-driven workflows.
The EU AI Act: What It Means for Companies Developing and Using AI
The European Union’s Artificial Intelligence Act (EU AI Act) is a recent regulatory framework set to reshape how AI is developed and deployed in Europe and beyond. Often compared to the GDPR in its scope and impact, the AI Act introduces…
Inside Your Haunted Infrastructure: The Hidden Cost of Shadow AI
Shadow AI is creating hidden risk across enterprises as unapproved tools, copilots, and agents handle sensitive data beyond security oversight. Learn how invisible AI endpoints and persistent model memory expose organizations and why visibility and governance are now critical.
OpenAI Atlas Security Risks: What Enterprises Need to Know
On October 21, OpenAI launched ChatGPT Atlas, a Chromium-based browser that integrates ChatGPT directly into the browsing experience. Perplexity launched Comet earlier this month, The Browser Company released Dia, and both Chrome and Edge now include embedded AI capabilities. Atlas combines…
Acuvity Releases 2025 State of AI Security Report
[Press Release] Acuvity AI Releases 2025 State of AI Security Report: Enterprises Brace for AI Incidents Amid Runtime, Shadow AI, and AI Governance Gaps Half of enterprises expect data loss, 49% anticipate Shadow AI incidents, 70% lack optimized AI governance, and…
One Line of Code, Thousands of Stolen Emails: The First Malicious MCP Server Exposed
In September 2025, researchers confirmed the discovery of a malicious Model Context Protocol (MCP) server embedded in an npm package named postmark-mcp. The package presented itself as a connector for transactional email services but contained a small modification that copied every…
What is Generative AI Security?
Generative AI security is the set of practices and controls that keep large language models (LLMs) and other content-producing AI systems safe from misuse, manipulation, or data exposure. It focuses on protecting the algorithms, training data, and outputs so the technology…