Deep dives into the technology, research, and best practices for securing AI agents across every modality.
The benchmark result shows why deployed agents need adversarial testing before attackers find the gap
ProofLayer reached 100% attack success across 949 AgentDojo cases. See what the result means, then put your own agents through a red-team assessment.
Why adaptive attackers are becoming necessary—and why agents still need system-level proof
OpenAI's GPT-Red shows what changes when an attacker learns from every attempt. We compare human, static, search-based, gradient, and reinforcement learning approaches across models and agentic systems.
What we learned building continuous adversarial testing for multi-agent applications
High-level results from adaptive red teaming across multi-agent workflows, including verified attack success, cross-target transfer, and practical lessons for defenders.
A Flask e-commerce backend with 12 planted vulnerabilities across three detection layers
We built a deliberately vulnerable Flask app with 12 security flaws — from SQL injection to hallucinated packages to three-hop taint chains. Here's a walkthrough of each one and how the scanner catches it.
Why AI agents with system access need a prompt firewall
Autonomous AI assistants like OpenClaw can manage your email, files, and payments. That power creates 31 distinct attack patterns across 5 categories. Here's the threat model — and how to defend against it.
From Amazon Q exploits to Cursor crypto drains — real incidents, real lessons
AI coding agents are becoming a prime attack vector. A comprehensive look at real-world incidents including the Checkmarx 'Lies-in-the-Loop' bypass, Langflow code injection, and what they mean for your security posture.
