Author

Wenbo Guo

Wenbo is the Head of Agent Security at Virtue AI, and Assistant Professor and Zhu Chair at the UCSB Computer Science Department.

Assistant Professor and Zhu Chair at the UCSB Computer Science Department. Wenbo is a recipient of multiple prestigious awards, including Google and Amazon research awards, IBM Ph.D. Fellowship and CCS Outstanding Paper Award. Going beyond academic research, he is the Head of Agent Security at Virtue AI.

Research

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

June 12, 2026

BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI

May 15, 2026

Decoding Trust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

May 5, 2026

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle

January 27, 2026

SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI

September 18, 2025

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

August 8, 2025

Posts

February 9, 2026

Openclaw Is A High-Value Target. Here’s How To Secure It.

OpenClaw is exploding right now. In the past week, OpenClaw has gone from “interesting agent demo” to mainstream viral tool, praised for actually executing tasks across real apps (chat, email, workflows) rather than just chatting. But what happens when users grant this agent unlimited access?

Resources

Report

OpenClaw Reveals Critical Agent Security Risks

Demo

AgentSuite Full Platform Walkthrough

Webinar

Agentic Security - Securing the Next Generation of AI Systems

Secure your autonomous enterprise with the team that defines the standard.

Don't let safety be the friction that grounds your innovation. Virtue AI is the launchpad for agentic systems, clearing the path from research to production-ready performance.

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.