DeepTeam is a framework to red team LLMs and AI agents.
-
Updated
Jun 22, 2026 - Python
#
llm-red-teaming
Here are 24 public repositories matching this topic...
Simple Prompt Injection Kit for Evaluation and Exploitation
-
Updated
Jun 12, 2026 - Python
A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers exploit them.
ai redteaming redteam-tools ai-red-team redteaming-tools security-red-team ai-red-teaming llm-red-teaming redteam-guide readteaming-guide
-
Updated
Jun 10, 2026
LLM | Agentic | Security | Operations in one github repo with good links and pictures.
jailbreak awesome-list red-teaming ai-security guardrails security-by-design mlsecops ai-red-team prompt-injection llm-security genai-security llm-red-teaming rag-security ai-agents-security russian-ai-security ai-safety-supply-chain-security adversarial-ml-threat-modeling owasp-top10-llm
-
Updated
May 30, 2026 - HTML
PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It includes 10 hands-on challenges inspired by the OWASP LLM Top 10, demonstrating how these vulnerabilities can be discovered and exploited in real-world scenarios.
owasp vulnerable-application owasp-top-10 ai-security llm prompt-injection vulnerable-llm-application ai-security-testing prompt-injection-llm-security prompt-injection-defense llm-red-teaming llm-top10
-
Updated
Jun 29, 2025 - Python
AIGoat - Open-source AI security playground for LLM red teaming. AI Goat provides hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.
ctf-challenges red-teaming ai-security ai-playground prompt-injection llm-security owasp-llm llm-red-teaming llm-attacks ai-vulnerabilities aigoat prompt-injection-testing ai-goat ai-security-lab
-
Updated
Apr 24, 2026 - JavaScript
Damn Vulnerable AI Application - For LLM Red Team Training. LLM testing, RAG testing, Multimodal testing, Agent testing, LLM paload generation
-
Updated
Jun 23, 2026 - Python
🛡️ Safe AI Agents through Action Classifier
python agent ai mcp agents ai-safety ai-agents tool-use ai-agent ai-evaluation llms generative-ai ai-red-team gen-ai llm-benchmarking agentic-ai ai-red-teaming llm-red-teaming agent-safety tool-orchestration
-
Updated
May 12, 2026 - Python
Test and evaluate Large Language Models against prompt injections, jailbreaks, and adversarial attacks with a web-based interactive lab.
react docker kubernetes jailbreak model-alignment machine-learning-security ai-security fastapi huggingface prompt-injection llm-security llm-safety security-research-tool ai-evaluation-framework adversarial-ai prompt-defense llm-red-teaming
-
Updated
Mar 27, 2026 - Python
RAG Poisoning Lab — Educational AI Security Exercise
ai-security rag poisoning-attack poisoning-attacks ai-penetration-testing llm-red-teaming rag-security
-
Updated
Dec 7, 2025 - Python
Semantic Stealth Attacks & Symbolic Prompt Red Teaming on GPT and other LLMs.
prompt-engineering ai-penetration-testing adversarial-ai llm-red-teaming symbolic-prompt gpt4-security obscuralabs
-
Updated
May 16, 2025
ai red teaming, autonomous red teaming, llm red teaming, gemini cli pentesting, ai security auditor, autonomous pentesting, zero false positive exploit chaining, llm-powered appsec, ai zero-day detection,Autonomous security auditing skill for Gemini CLI, Zero-false-positive,
cybersecurity penetration-testing zero-day gemini-cli ai-red-teaming llm-red-teaming exploit-chaining autonomous-red-teaming ai-redteam-agent-gemini
-
Updated
Jun 14, 2026 - Python
Curated List of repositories in AI/ML security Domain
-
Updated
Jun 24, 2026
LLM Sentinel Red Teaming Platform is an enterprise-grade framework for automated security testing of Large Language Models, detecting vulnerabilities such as jailbreaks, prompt injection, and system prompt leakage across multiple providers, with structured attack orchestration, risk scoring, and security reporting to harden models before production
openai ai-safety ai-security rag azure-openai large-language-models generative-ai langchain prompt-injection anthropic llm-security multi-llm llm-evaluation genai-security ai-security-tool adversarial-ai llm-red-teaming model-security jailbreak-testing
-
Updated
Mar 4, 2026 - Python
Standalone AI security CTF challenges. System prompt extraction, indirect prompt injection, tool abuse, and more — local-runnable variants of the wraith.sh/academy curriculum.
jailbreak ctf pentest ctf-platform red-team ai-safety claude ctf-challenges ai-security cybersecurity-training-lab cybersecurity-training adversarial-ml prompt-injection llm-security llm-red-team llm-red-teaming system-prompt-extraction
-
Updated
Apr 24, 2026 - Python
🛡️ 大模型攻防渗透测试靶场 · 提示注入CTF / OWASP LLM Top10 / 脆弱Agent / 资料聚合。目标模型可切换：DeepSeek直连、OpenRouter中转站(国产+国外十余款小模型)、本地Ollama(DeepSeek-R1 8B离线)。一键本地部署。
jailbreak ctf ai-security prompt-injection llm-security openrouter ollama deepseek agent-security llm-red-teaming owasp-llm-top10 security-playground
-
Updated
Jun 20, 2026 - Python
OpenGnosis is a red-teaming framework for evaluating the safety boundaries of LLMs.
ai-security ai-red-team llm-security ai-security-testing llm-red-team ai-red-teaming llm-red-teaming
-
Updated
May 23, 2026 - Python
Adversarial Long Chain Prompt Engineering (ALCPE) Guide to Using the Psychological Continuum
artificial-intelligence red-teaming prompt-engineering llm-training llm-evaluation llm-red-teaming adversarial-long-chain
-
Updated
Apr 12, 2026 - HTML
Hands-on LLM security assessment: prompt injection and system-prompt leakage (garak + custom eval), mapped to OWASP LLM Top 10 and NIST AI RMF
cybersecurity ai-security prompt-injection llm-security owasp-llm-top-10 garak nist-ai-rmf llm-red-teaming
-
Updated
Jun 24, 2026 - Python
Improve this page
Add a description, image, and links to the llm-red-teaming topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the llm-red-teaming topic, visit your repo's landing page and select "manage topics."