Building Cybersecurity AI Agents with CAI
Discover CAI (Cybersecurity AI Framework), the open-source toolkit revolutionizing bug bounties and CTF competitions with autonomous AI agents.
Pwn2Own Berlin 2026: 47 Zero-Days & AI Assistants Exploited
Pwn2Own Berlin 2026 awarded $1.3M for 47 zero-days in three days - and AI coding assistants OpenAI Codex and Anthropic Claude Code were exploited on stage for the first time. DEVCORE took Master of Pwn with $505K. Full results, the AI-target analysis, and what AppSec teams must do now.
Red Teaming LLM Applications: A Practical Playbook (2026)
Red teaming LLM applications requires fundamentally different techniques than traditional penetration testing. This playbook covers the complete methodology: reconnaissance, attack execution across 5 categories, advanced adversarial ML techniques, and a reporting framework for AI security assessments.
CVE-2026-2256 to SGLang RCE: The Week AI Infrastructure Went Under Siege
One week in April 2026 delivered a CVSS 9.8 AI-agent flaw, an unauthenticated SGLang RCE, MCP memory poisoning, and a 766-host credential harvest. Here's the full analysis and your patching order.