Whitebox & Blackbox red-teaming framework for LLMs & Agentic AI apps. It analyzes your app's source code to discover tools, roles, and guardrails, then generates new attacks chains across several categories and adapts over multiple multi turn rounds to find vulnerabilities
security penetration-testing red-team data-exfiltration ai-agents vulnerability-scanner security-testing ai-security white-box llm prompt-injection red-teaming-tools llm-security agentic-ai ai-security-tool tool-misuse agent-security-tools
-
Updated
May 27, 2026 - Python