Features
Prompt injection detection
Jailbreaking attack automation
Attack techniques: AdvPrefix, AutoDAN-Turbo, PAIR, TAP, FlipAttack, BoN, h4rm3l, CipherChat, PAP, Static Template
Pre-built benchmark datasets (AgentHarm, JailbreakBench, HarmBench, AdvBench, StrongREJECT, etc.)
Multi-framework agent support (Google ADK, OpenAI SDK, LiteLLM, LangChain, Ollama, vLLM)
Modular attack engine with generator and judge LLMs
Real-time terminal UI with attack progress and visualizations
Optional cloud sync via API key
Custom file dataset import (JSON/CSV/JSONL/TXT)
HuggingFace dataset integration
AI discovery and shadow AI reconnaissance
Automated AI red teaming with continuous testing
Psychometric agent profiling and fingerprinting
AI attack surface enumeration and mapping
Runtime AI protection and context-driven guardrails
GuardBuster tool for AI guardrail evaluation
Exploitable risk detection prioritizing high-impact findings
AI security risk compliance reporting (GRC)
Automated AI agent hardening
Integration with CI/CD pipelines and Burp Suite
One-click deployment without specialized expertise
AI-BOM and shadow AI risk exposure
Agent-native reconnaissance before attack execution
Zero-day exploit research and public disclosure support
Supports AI chatbots, applications, agents, and infrastructure
