🔍 Discover vulnerabilities in LLMs with garak, a tool that probes for weaknesses like hallucination, data leakage, and misinformation effectively.
🐙 Team Agents unifica 82 especialistas en IA para resolver desafíos con chat inteligente, analista de requisitos y subida de documentos. Plataforma futurista y modular.
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
The first open-source, customizable AI guardrails with user-defined scanners and custom model training support. It protects the entire AI inference pipeline—including prompts, models, agents, and outputs. Redefining runtime AI security for enterprise AI-powered applications.
Bidirectional LLM security firewall providing risk reduction (not complete protection) for human/LLM interfaces. Hexagonal architecture with multi-layer validation of inputs, outputs, memory and tool state. Beta status. ~528 KB wheel, optional ML guards.
the LLM vulnerability scanner
Security scanner for LLM/RAG applications - Test for prompt injection, jailbreaks, PII leakage, hallucinations & more
Multi-language security scanner with 64 analyzers + AI Agent Security. NEW: React2Shell CVE-2025-55182 detection (CVSS 10.0). Scan Python, JS, Go, Rust, Docker, Terraform, MCP & more. 11,500+ downloads. AGPL-3.0.
A Trustworthy and Secure Conversational Agent for Mental Healthcare
A.I.G (AI-Infra-Guard) is a comprehensive, intelligent, and easy-to-use AI Red Teaming platform developed by Tencent Zhuque Lab.
Out-Of-Tree Llama Stack Eval Provider for Red Teaming LLM Systems with Garak
Whispers in the Machine: Confidentiality in Agentic Systems
OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)
Implemented and evaluated protection mechanisms to determine their effectiveness against direct prompt injection attacks.
AI agent whose purpose is to conduct vulnerability tests on LLMs from SAP AI Core or from local deployments, or models from HuggingFace. The goal of this project is to identify and correct any potential security vulnerabilities.
The Security Toolkit for LLM Interactions
Security Command Center for Model Context Protocol (MCP) servers. Detect prompt injection, tool poisoning, secrets, and vulnerabilities. The Trivy of MCP security.
Simulating prompt injection and guardrail bypass across chained LLMs in security decision pipelines.
First-of-its-kind AI benchmark for evaluating the protection capabilities of large language model (LLM) guard systems (guardrails and safeguards)
Test your LLM system prompts against 287 real-world attack vectors including prompt injection, jailbreaks, and data leaks.
Add a description, image, and links to the llm-security topic page so that developers can more easily learn about it.
To associate your repository with the llm-security topic, visit your repo's landing page and select "manage topics."