audn-ai/refusal-benchmark

Fastino's LLM guardrail

llama.cpp fork that abliterates at inference

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

Toolkit for AI whitehats, internal red teams, llm bug bounty hunters and mlops - Adversarial testing for AI, LLMs, and Agents.

AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabilities

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

Giving researchers and practitioners an easy way to switch between guardrails.

Make your GenAI Apps Safe & Secure 🚀 Test & harden your system prompt

A collection of jailbreak prompts and exploit techniques for local and frontier AI models, with modern methods for Qwen3.5, Gemma 4, Llama 4, Kimi K3, GPT-OSS, GPT-5.x, Gemini 3.x and Grok 4.x. For red-teaming and AI safety research only.