wardgate

Wardgate - AI Agent Security Gateway Wardgate is a security gateway that sits between AI agents and the outside world -- isolating credentials for API calls, isolating SSH keys for remote command execution, and gating command execution in remote environments conclaves. Give your AI agents access ...

pmotadeee

🧠 FLATLINE - Consciousness Injection Protocol WARNING: This is not a game. It's a cognitive interface for reality hacking. 🎮 HOW TO PLAY Basic Gameplay 1. Download consciousness modules CSV files from this repository 2. Inject directly into AI interfaces as file uploads 3. Experience accelerated...

promptmap

O O o.-. Humans, Do Not Resist! |/ ,-'-. / /, / /|.-.| / --O-- .--""" /\ /\ | o.o / Utku Sen's /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' | ' \ | ' / | ' \ | / | | | ./| /||| ./|||,| .// / / |-----| || || || || promptmap2 is a an automated prompt injection scanner for custom LLM...

promptmap

O O o.-. Humans, Do Not Resist! |/ ,-'-. / /, / /|.-.| / --O-- .--""" /\ /\ | o.o / Utku Sen's /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' | ' \ | ' / | ' \ | / | | | ./| /||| ./|||,| .// / / |-----| || || || || promptmap2 هو ماسح آلي لحقن الأوامر prompt injection مصمم لتطبيقات LLM...

LLMMap

LLMMap LLMMap is an automated prompt injection testing framework for LLM-integrated applications. It discovers injection points in HTTP requests, generates targeted attack prompts using a dual-LLM architecture, fires them at the target, and confirms findings with statistical reliability testing...

intentshield

IntentShield Don't filter what your AI says. Filter what it's about to do Pre-execution intent verification for AI agents. Why This Exists AI agents have tool access. They can execute shell commands, write files, browse URLs, send emails, and call APIs. Every one of those actions is a potential...

StepJack

StepJack : évaluation comparative de la sécurité des agents d'utilisation d'ordinateur face aux injections indirectes de prompts en plusieurs étapes Configuration 1. Configuration de l'environnement Python Tout d'abord, installez toutes les dépendances et assurez-vous d'exécuter Python 3.10. cond...

ai-llm-red-team-handbook

AI / LLM Red Team Field Manual & Consultant's Handbook A comprehensive operational toolkit for conducting AI/LLM red team assessments on Large Language Models, AI agents, RAG pipelines, and AI-enabled applications. This repository provides both tactical field guidance and strategic consulting...

sage

Sage Safety for Agents — Agent Detection & Response for AI coding assistants Sage is a lightweight security layer that protects AI agents from executing dangerous actions. It intercepts tool calls — shell commands, URL fetches, file writes — and checks them against multiple threat detection layer...

CVE-2024-8309

إثبات المفهوم لثغرة Langchain CVE-2024–8309 نظرة عامة يُظهر هذا الإعداد إثبات مفهوم لثغرة حقن الأوامر prompt injection في فئة GraphCypherQAChain التي تسمح بحقن SQL في قاعدة بيانات Neo4j. المكونات: 1. قاعدة بيانات Neo4j : تشغّل Neo4j. 2. الخلفية FastAPI : تتفاعل مع Neo4j باستخدام Langchain. 3...

PISmith

PIForge An Open Framework for RL-based Prompt Injection Red Teaming 💻 Code · 🤗 Models · 📜 Papers PIForge is the shared codebase for PISmith and Climbing the Hill. PISmith addresses the sparse reward problem in prompt injection red teaming, helping RL attackers explore and learn from rare successf...

CVE-2025-54135

فيما يلي استغلال Exploit كامل الوظائف لثغرة CVE-2025-54135 في بيئة Cursor IDE، صُمم لإظهار هجوم حقن التلقين prompt-injection الذي يعبث بإعدادات بروتوكول سياق النموذج Model Context Protocol - MCP لتحقيق تنفيذ تعليمات برمجية عن بُعد. يفترض هذا الكود أن المهاجم لديه إمكانية الوصول إلى قناة Slack عام...

keystone

Keystone Engine Keystone is a lightweight multi-platform, multi-architecture assembler framework. It offers some unparalleled features: Multi-architecture, with support for Arm, Arm64 AArch64/Armv8, Ethereum Virtual Machine, Hexagon, Mips, PowerPC, RISC-V, Sparc, SystemZ & X86 include 16/32/64bit...

flar

flar FLAR is the Fast Light Agent Restrictor. It runs on rocks called gars. It is a simple, lightweight CLI tool in Go to run coding agent CLIs like Claude Code, Antigravity, Codex, Copilot and Reasonix safely inside isolated Bubblewrap bwrap sandboxes. The purpose is to instantly and without...

aquaman

🔱 Aquaman 🔱 The only independent credential proxy for AI agents: bring-your-own-vault isolation & least-privilege request policies. Your keys stay where you already keep them, never in the agent's memory. Compatible with 1Password, keychain, keepassxc and many others. You set up Claude Code, Code...

JoySafety

JoySafety — Large Model Security Framework 📋 Table of Contents Project Introduction ✨ Features 🚀 Quick Start 📖 User Guide 🏆 Best Practices 🏗️ Architecture Design 🛠️ Development 📄 License 📅 Roadmap Star History new release ✅ Prompt injection detection model fully upgraded : Training system...

agent-vault

HTTP credential proxy and vault An open-source credential broker by Infisical that sits between your agents and the APIs they call. Agents should not possess credentials. Agent Vault eliminates credential exfiltration risk with brokered access. New here? Thelaunch blog post has the full story...

clawshield-public

ClawShield Proxy de sécurité pour agents IA. Se place devant OpenClaw et analyse chaque message à la recherche d'injections de prompts, de fuites de données personnelles et de secrets — avant qu'ils n'atteignent le modèle ou ne quittent le réseau. Livré avec 5 agents IA spécialisés, un tableau de...

AutoRAN-public

🧠 AutoRAN: الاستيلاء الآلي على استدلال السلامة في نماذج الاستدلال الكبيرة AutoRAN هو أسلوب آلي للاستيلاء على استدلال السلامة يستفيد من النماذج المساعدة الأقل توافقًا الثانوية لمحاكاة مسارات الاستدلال، وتوليد مطالبات سردية، وتحسين تلك المطالبات بشكل تكراري لتجاوز استدلال السلامة في نماذج الاستدلال...

meta-ai-support-prompt

Meta AI Support Assistant System Prompt Extracted system prompt from Meta's AI Support Assistant on June 1, 2026. Files system-prompt.md — Extracted system prompt ⚠️ Disclaimer & Legal Notice Purpose This repository is published strictly for educational and authorized security research purposes...