Open-source adversary emulation for AI agents and MCP servers.

SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

Code scanner to check for issues in prompts and LLM calls

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

Static security scanner for AI agents. Catches prompt injection, runaway loops, missing oversight, and compliance gaps across 21 frameworks. Use from Claude Code, Cursor, ChatGPT (MCP), the CLI, or GitHub Actions.

AI security and prompt injection payload toolkit

A purposely vulnerable voice agent application for security practitioners to practice exploiting voice-based (and text based) AI systems.

Basilisk — Open-source AI red teaming framework with genetic prompt evolution. Automated LLM security testing for GPT-4, Claude, Grok, Gemini. OWASP LLM Top 10 coverage. 32 attack modules.

An intentionally vulnerable AI chatbot to learn and practice AI Security.

AIDEFEND MCP is a local-first AI Security Defensive Assistant that brings the full AIDEFEND countermeasure library into your environment and turns static knowledge into actionable protection for LLMs and agentic AI systems — privately, securely, and on-device.

Open-Source Prompt Injection Scanner for AI agents. 225 detection patterns across 17 categories, 15 languages. REST API, EU AI Act compliance mapping, <10ms latency.

Türkçe yapay zeka güvenliği için tek çatı: rehber serisi, uygulamalı akademi (ai.altaysec.com.tr), araştırma & deneyler (deney.altaysec.com.tr) ve açık kaynak araçlar.

OWASP LLM Top 10 (2025) Türkçe Kapsamlı Rehber. Büyük Dil Modelleri (LLM) için en kritik 10 güvenlik riskini, gerçek saldırı senaryolarını ve savunma stratejilerini içeren teknik dökümantasyon. Türkiye'nin ilk LLM Security yazı serisinin 3. bölümü.

AI Assurance Framework (AIAF Sentry) is an open-source platform designed to improve the security, trustworthiness, resilience, and governance of Artificial Intelligence systems through continuous assurance methodologies. The framework enables organizations to assess AI security risks, validate governance controls, and monitor AI deployments.

The Citadel is not just a training platform; it is a battleground. As AI systems integrate deeper into our critical infrastructure, the attack surface expands exponentially. This application is a purpose-built LLM Pentesting Environment designed to simulate real-world threats against Large Language Models.

Local-first LLM adversarial assurance lab for mapping attacks to controls, evidence, and framework readiness.

LLM Security & OWASP LLM Auditing Framework

Python + SQL toolkit for LLM threat intelligence — flags prompt injection, jailbreaks, and data exfiltration mapped to OWASP LLM Top 10 (2025) & MITRE ATLAS.

Security & runtime checklist for moving LLM agents from demo to production: HITL gates, idempotency, prompt injection boundaries, tool risk classification (CC BY 4.0).