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 servers. Koi Security breaks down real-world incidents behind multiple categories, including two cases cited by OWASP, showing how agent tools and runtime behavior are being abused.

• Koi Security
• December 29, 2025
• 10:00 AM
• 0

Brave browser starts testing agentic AI mode for automated tasks

Brave has introduced a new AI browsing feature that leverages Leo, its privacy-respecting AI assistant, to perform automated tasks for the user.

• Bill Toulas
• December 11, 2025
• 06:03 PM
• 5

New Webinar: Choose Your Own Investigation — Browser Attack Edition

Modern attacks have shifted focus to the browser, yet detection tools remain largely blind to the crucial activity happening there.

Join Push Security on February 11th for an interactive "choose-your-own-adventure" webinar on ClickFix, credential phishing, and other in-browser attacks we've observed in the wild.

• Push Security Sponsorship

Google Chrome adds new security layer for Gemini AI agentic browsing

Google Chrome is introducing a new security architecture designed to protect upcoming agentic AI browsing features powered by Gemini.

• Bill Toulas
• December 08, 2025
• 01:08 PM
• 2

How Agentic BAS AI Turns Threat Headlines Into Defense Strategies

Picus Security explains why relying on LLM-generated attack scripts is risky and how an agentic approach maps real threat intel to safe, validated TTPs. Their breakdown shows how teams can turn headline threats into reliable defense checks without unsafe automation.

• Picus Security
• December 08, 2025
• 10:02 AM
• 0

Extending Zero Trust to AI Agents: “Never Trust, Always Verify” Goes Autonomous

As AI agents gain autonomy to act, decide, and access data, traditional Zero Trust models fall short. Token Security explains how to extend "never trust, always verify" to agentic AI with scoped access, continuous monitoring, and human accountability.

• Token Security
• November 12, 2025
• 10:25 AM
• 0

Rethinking identity security in the age of autonomous AI agents

AI agents now make decisions and access systems on their own, creating identity blind spots traditional tools can't see. Learn how Token Security brings identity-first security to agentic AI — making every agent verified, owned, and accountable.

• Token Security
• October 30, 2025
• 10:00 AM
• 0