CKA-Agent
ActiveDescription
Research tool for bypassing commercial LLM guardrails to evaluate and improve the effectiveness of LLM safety defense mechanisms.
Related Projects
Pytector
40 · Python
Easy to use LLM prompt injection detection and prompt input sanitization Python package with multiple detection methods and custom rules.
prompt-injectiondetectionsanitization +2
Garak
7.6k · HTML
NVIDIA's open-source LLM vulnerability scanner that automatically detects security issues in language models including safety vulnerabilities, hallucination tendencies, jailbreak risks, and prompt injection attacks.
llm-securityvulnerability-scannerllm-evaluation +2
AI-Infra-Guard
3.5k · Python
Tencent's full-stack AI red teaming platform integrating OpenClaw security scanning, agent scanning, skills scanning, MCP scanning, AI infrastructure scanning, and LLM jailbreak evaluation.
ai-securityred-teamingllm-security +2
LLM Jailbreaking Defense
60 · Python
A lightweight library for LLM jailbreaking defense with multiple defense strategies to protect large language models from jailbreak attacks.
jailbreak-defensellm-securitysafety +1