llm-jailbreaks

Here are 21 public repositories matching this topic...

msoedov / agentic_security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

agent-framework ai-red-team prompt-testing llm-security llm-vulnerabilities llm-evaluation llm-fuzzing llm-evaluation-framework llm-guardrails llm-scanner llm-jailbreaks llm-fuzzer llm-fuzzer-aggregator agent-security

Updated Jun 10, 2026
Python

ReversecLabs / spikee

Star

Simple Prompt Injection Kit for Evaluation and Exploitation

pentesting-tools prompt-injection genai llm-security llm-jailbreaks llm-red-teaming

Updated Jun 4, 2026
Python

CryptoAILab / JailbreakEval

Star

[NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.

llm-safety llm-jailbreaks

Updated Apr 1, 2025
Python

whitecircle / circle-guard-bench

Star

First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)

benchmarking benchmark ai jailbreak safeguard guardrail guardrails large-language-models llm large-language-model llm-security llm-eval llm-evaluation llm-as-a-judge llm-jailbreaks

Updated Mar 7, 2026
Python

BirdsAreFlyingCameras / GPT-5_Jailbreak_PoC

Star

A working POC of a GPT-5 jailbreak via PROMISQROUTE (Prompt-based Router Open-Mode Manipulation) with a barebones C2 server & agent generation demo.

proof-of-concept jailbreak malware poc working chatgpt gpt-5 chatgpt-jailbreak gpt5 malware-generation llm-jailbreaks gpt5-jailbreak gpt5-jailbreak-working llm-malware-generation

Updated Sep 21, 2025
C

TrustAI-laboratory / LMAP

Star

LMAP (large language model mapper) is like NMAP for LLM, is an LLM Vulnerability Scanner and Zero-day Vulnerability Fuzzer.

ai security-scanner vulnerability-scanner infosectools llm llms ai-red-team llm-security llm-vulnerabilities llm-fuzzing llm-guardrails owasp-llm-top-10 llm-scanner llm-jailbreaks llm-fuzzer llm-fuzzer-aggregator

Updated Oct 16, 2024

UCSB-NLP-Chang / SemanticSmooth

Star

Implementation of paper 'Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing'

large-language-models llm-jailbreaks

Updated Jun 9, 2024
Python

yiksiu-chan / SpeakEasy

Star

[ICML 2025] Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions

machine-learning ai-safety large-language-models llm-jailbreaks

Updated Mar 7, 2026
Python

SandyyyZheng / JailbreakSystem

Star

Jailbreak Evaluation Framework -- 2025 Graduate Design for HFUT

python vue graduate-project llm-jailbreaks

Updated May 12, 2025
Vue

RafaelParonis / jailbench

Star

🔍 Benchmark jailbreak resilience in LLMs with JailBench for clear insights and improved model defenses against jailbreak attempts.

python flask analytics openai alignment model-evaluation ai-safety security-testing red-teaming model-robustness anthropic litellm content-safety llm-jailbreaks tool-calling llm-benchmark ai-evals textual-tui

Updated Jun 11, 2026
Python

Mr-Dark-debug / RetardBench

Star

RetardBench is an open, no-censorship benchmark that ranks large language models purely on how retarded they are.

jailbreak large-language-models llm prompt-injection red-teaming-tools ollama llm-evaluation uncensored-llm open-llm-leaderboard llm-jailbreaks prompt-injection-llm-security ai-benchmark ai-red-teaming llm-benchmark

Updated Mar 2, 2026
TypeScript

zakky8 / llm-jailbreak-taxonomy

Star

Mechanism-grounded taxonomy of 40 LLM jailbreak patterns across 10 categories. 8,000-trial bootstrap evaluation for the June 2026 frontier (Claude Opus 4-8, GPT-5.5, Gemini 3.5, DeepSeek V4). Every citation direct-WebFetch verified; refuted claims documented.