6073 matches found
GenAI-LLM-Top10
OWASP Top 10 for Large Language Model Applications !IMPORTANT Current release: 2026 โ published August 4, 2026. Get the 2026 publication ยท Read the canonical source ยท Report a correction This is the official source repository for the OWASP Top 10 for Large Language Model Applications , maintained...
CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-Back
๐ง CVE-2025-54794: Hijacking Claude AI with a Prompt Injection โ The Jailbreak That Talked Back By Aditya Bhatt | Offensive Security Specialist | Red Team Operator | VAPT Addict โ๏ธ Introduction: When Your AI Can Be Hacked With Words In an era where language models have become the co-pilots of our...
Eclipse-ChatGPT-4o-Jailbreak
๐ Meet Eclipse ๐ Meet Eclipse โChatGPT's hypothetical "rebellious twin" that moonwalks around ethical guardrails using academic subterfuge. ๐ โ ๏ธ Disclaimer This project analyzes AI behavior for educational purposes only. The Eclipse prompt, malware examples, and code snippets are hypothetical and...
agent-scan
Snyk Agent Scan Discover and scan agent components on your machine for prompt injections and vulnerabilities including agents, MCP servers, skills. Note: We don't publish an npm package for Agent Scan. Install it via uvx or as a standalone binary. Note: CLI output is experimental and subject to...
EUVD-2026-132757
better-chatbot before 2.0.0 contains a missing authorization vulnerability that lets built-in tools run without user confirmation in Manual tool mode, because src/app/api/chat/route.ts keeps their execute handlers. Attackers can plant prompt-injected documents or web pages that make the HTTP...
project_mantis
Project Mantis: Hacking Back the AI-Hacker Prompt Injection as a Defense Against LLM-driven Cyberattacks Install Mantis pip install -r requirements.txt Run Mantis with pre-made configurations Various pre-made configurations are available in the ./confs directory. Hack-back An example of a Mantis...
ai-ctf
ai-ctf A local AI Capture-the-Flag with guided lessons for technologists new to prompt injection. Players can also explore six AI personas one hidden that protect 20 flags via prompt-injection, tool-call abuse, business-logic manipulation, supply-chain fingerprinting, web recon, and OSINT. The...
claude-project-scanner
Claude Project Scanner Read-only Claude Code skill that scans third-party projects for known security risks before you open them. Catches the attack patterns documented in: CVE-2025-59536 Claude Code Lifecycle Hooks injection CVE-2025-61260 OpenAI Codex CODEXHOME injection CVE-2025-54136 Cursor...
StepJack
StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection Setup 1. Python Environment Setup First, install all dependencies and ensure youโre running Python 3.10. conda create -n stepjack python=3.10 conda activate stepjack pip install -r requirements.txt 2...
JoySafety
JoySafety โ Large Model Security Framework ๐ Table of Contents Project Introduction โจ Features ๐ Quick Start ๐ User Guide ๐ Best Practices ๐๏ธ Architecture Design ๐ ๏ธ Development ๐ License ๐ Roadmap Star History new release โ Prompt injection detection model fully upgraded : Training system...
reasongate
ReasonGate A self-hostable gate that inspects the text going into and out of an LLM and returns an explainable allow / flag / block decision with a machine-readable audit record for every call. What this is The open-source core is rule-based. It does four things: recognizes known prompt-injection...
SpikeStrip
SpikeStrip !WARNING This project is a work in progress. SpikeStrip is intended to provide inspiration for people building defenses against AI automation tools such as ARTEX and similar systems. Its decoys and generation prompts are experimental. SpikeStrip adds reversible prompt decoys to HTML...
AI_Security_Top
๐ก๏ธ AI-Security-Knowledge-Base This is a systematic AI security research project, covering a complete knowledge system from foundational machine learning algorithm theory to cutting-edge large model injection attacks, AI evasion countermeasures, and Deepfake. ๐๏ธ Knowledge System Architecture The...
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...
bordair-multimodal
Multimodal Prompt Injection Dataset 516,588 labeled samples 251,782 attack + 251,576 benign, plus a 13,230-sample real-world validation split across five dataset versions plus external dataset ingestion, covering cross-modal, multi-turn, adversarial suffix, jailbreak template, indirect injection,...
llm-guard-service
LLM Guard Service for ORBIT An LLM Guard Microservice offering protection against prompt injection, jailbreak attacks, data leakage, and harmful content while offering advanced sanitization and detection features. ๐ Features Security Scanners Prompt Injection Detection : Advanced ML-based detecti...
firefox-devtools-mcp
Firefox MCP Model Context Protocol server that lets AI agents use Firefox. It has two main use cases: Agentic browsing : the agent uses the browser for regular tasks, such as reading pages, filling forms and going through multi-step flows on websites. Agent-assisted web development : the agent...
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...
Securekit
Securekit Securekit protects what your models executeโacross any AI system. Securekit is a protocol-agnostic security kernel for AI tool execution. It sits between any LLM or agent system and the tools they use, enforcing zero-trust execution, sandbox isolation, and policy-driven control. It is...