stacklok/toolhive

ToolHive makes deploying MCP servers easy, secure and fun

Language: Go - Size: 8.65 MB - Last synced at: about 9 hours ago - Pushed at: about 9 hours ago - Stars: 1,141 - Forks: 107

tokra-ai/tokra-shield

Open-source, in-band policy firewall for AI — signed, version-locked rules; zero-leak by default.

Language: Python - Size: 8.67 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 0 - Forks: 0

fyankov96/agentic-soc-analyst

AI-powered SOC analyst for Azure Sentinel threat hunting with GPT and VirusTotal integration.

Language: Python - Size: 87.9 KB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 0 - Forks: 0

edward-playground/aidefense-framework

An open-source knowledge base of defensive countermeasures to protect AI/ML systems. Features interactive views and maps defenses to known threats from frameworks like MITRE ATLAS, MAESTRO, and OWASP.

Language: HTML - Size: 2.22 MB - Last synced at: 1 day ago - Pushed at: 2 days ago - Stars: 45 - Forks: 12

ojaaaaannnn/SecuSploitX

🛠️ Create and automate advanced penetration testing with SecuSploitX, an open-source toolkit designed for cybersecurity professionals and enthusiasts.

Language: HTML - Size: 39.8 MB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 0 - Forks: 0

Yosuraki/claude4-audit-recon

🐙 Ethical red-team audit of Claude 4 with clear introspection and policy visibility. Includes JSON data and Python tooling; Mermaid diagrams map model behavior.

Language: Python - Size: 27.6 MB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 0 - Forks: 0

roynaldo1234/meta-ai-bug-bounty

Meta AI Bug Bounty focuses on vulnerabilities in Instagram's Group Chat feature, revealing critical security risks. Join us in improving AI safety and explore our findings on GitHub! 🐙✨

Size: 141 KB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 0 - Forks: 0

jiep/offensive-ai-compilation

A curated list of useful resources that cover Offensive AI.

Language: HTML - Size: 18.1 MB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 1,274 - Forks: 136

ai-for-developers/awesome-ai-coding-tools

A curated list of AI-powered coding tools

Size: 194 KB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 827 - Forks: 75

THUYimingLi/backdoor-learning-resources

A list of backdoor learning resources

Size: 1.07 MB - Last synced at: 2 days ago - Pushed at: about 1 year ago - Stars: 1,127 - Forks: 173

splx-ai/agentic-radar

A security scanner for your LLM agentic workflows

Language: Python - Size: 18 MB - Last synced at: 2 days ago - Pushed at: about 1 month ago - Stars: 698 - Forks: 82

javidahmed64592/cyber-query-ai

Ollama-powered cybersecurity assistant for ethical penetration testing and security research.

Language: TypeScript - Size: 547 KB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 0 - Forks: 0

0x6f677548/copilot-instructions-unicode-injection

Proof of Concept (PoC) demonstrating prompt injection vulnerability in AI code assistants (like Copilot) using hidden Unicode characters within instruction files (copilot-instructions.md). Highlights risks of using untrusted instruction templates. For educational/research purposes only.

Size: 1.48 MB - Last synced at: 3 days ago - Pushed at: 4 months ago - Stars: 4 - Forks: 0

taladari/rag-firewall

Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

Language: Python - Size: 115 KB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 13 - Forks: 0

Feirbrand/forgeos-public

AI security research: threat intelligence codex (513+ vectors), symbolic SIF framework, field-validated Phoenix recovery protocols, hybrid vulnerability analysis, CTTA research. Apache 2.0

Language: Python - Size: 6.12 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 1 - Forks: 0

RHEcosystemAppEng/sast-ai-orchestrator

Controller for SAST-AI-Workflows. This project schedules, monitors, and serves workflow info to REST clients 🧠📡

Language: Java - Size: 476 KB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 0 - Forks: 0

stacklok/toolhive-studio

ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agents

Language: TypeScript - Size: 6.63 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 44 - Forks: 4

chaitin/MonkeyCode

企业级 AI 编程助手，支持私有化离线部署，兼容第三方及本地化大模型，具备企业级管理面板，具备代码安全功能。

Language: TypeScript - Size: 10.5 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 1,390 - Forks: 179

OWASP/www-project-promptme

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.

Language: Python - Size: 81.1 MB - Last synced at: 3 days ago - Pushed at: 18 days ago - Stars: 5 - Forks: 0

GopherSecurity/gopher-mcp

MCP C++ SDK - Model Context Protocol implementation in CPP with enterprise-grade security for servers and clients.

Language: C++ - Size: 8.53 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 24 - Forks: 0

IronCoreLabs/ironcore-alloy

A unified SDK for IronCore encryption operations including vector encryption for AI data

Language: Rust - Size: 1.26 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 12 - Forks: 3

fiddlecube/compliant-llm

Build Secure and Compliant AI agents and MCP Servers. YC W23

Language: Python - Size: 58.8 MB - Last synced at: about 15 hours ago - Pushed at: 3 months ago - Stars: 148 - Forks: 8

j1ake/prompt-injector

🎯 Generate AI security test conversations with this experimental TypeScript library for prompt injection attacks, designed for security professionals.

Language: TypeScript - Size: 438 KB - Last synced at: 6 days ago - Pushed at: 7 days ago - Stars: 0 - Forks: 0

LetterLiGo/SafeGen_CCS2024

[CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models

Language: Python - Size: 2.66 MB - Last synced at: 4 days ago - Pushed at: 2 months ago - Stars: 135 - Forks: 11

christian-taillon/open-webui-pipelines

Pipelines for OpenWebUI

Language: Python - Size: 31.5 MB - Last synced at: 7 days ago - Pushed at: 9 days ago - Stars: 1 - Forks: 0

The-Art-of-Hacking/h4cker

This repository is primarily maintained by Omar Santos (@santosomar) and includes thousands of resources related to ethical hacking, bug bounties, digital forensics and incident response (DFIR), artificial intelligence security, vulnerability research, exploit development, reverse engineering, and more.

Language: Jupyter Notebook - Size: 139 MB - Last synced at: 9 days ago - Pushed at: 9 days ago - Stars: 22,720 - Forks: 4,288

GPierce9/Vault-Protocol-v2.6-Safer-AI-by-Design

Vault Protocol is an integrated, trauma-informed safety architecture built inside the model’s runtime, not bolted on. The upshot is (1) lower cost, (2) lower damage ceiling, and (3) humane guardrails. By weaving guardrails into the system’s own process, Vault aims for layered safety without sacrificing utility or dignity.

Size: 229 KB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 0 - Forks: 0

AUX-441/SecuSploitX

Sploit -- All-in-one, AI-powered cybersecurity toolkit for web, network, and phishing tests. Modular, cross-platform, Docker-ready, with GUI & CLI. Open source by AUX-441 Team.

Language: HTML - Size: 39.8 MB - Last synced at: 11 days ago - Pushed at: 11 days ago - Stars: 1 - Forks: 0

Giskard-AI/giskard-oss

🐢 Open-Source Evaluation & Testing library for LLM Agents

Language: Python - Size: 176 MB - Last synced at: 11 days ago - Pushed at: 12 days ago - Stars: 4,835 - Forks: 352

LLAMATOR-Core/llamator

Framework for testing vulnerabilities of large language models (LLM).

Language: Python - Size: 4.58 MB - Last synced at: 7 days ago - Pushed at: 19 days ago - Stars: 138 - Forks: 13

GH05TCREW/PentestAgent

All-in-one offensive security toolbox with AI agent and MCP architecture. Integrates tools like Nmap, Metasploit, FFUF, SQLMap. Enables pentesting, bug bounty hunting, threat hunting, and reporting. RAG-based responses with local knowledge base support.

Language: Python - Size: 259 KB - Last synced at: 11 days ago - Pushed at: 3 months ago - Stars: 313 - Forks: 54

AnonKryptiQuz/XSSGAI

XSSGAI is the first-ever AI-powered XSS (Cross-Site Scripting) payload generator. It leverages machine learning and deep learning to create novel payloads based on patterns from real-world XSS attacks.

Language: Jupyter Notebook - Size: 6.9 MB - Last synced at: 3 days ago - Pushed at: about 1 month ago - Stars: 28 - Forks: 6

ericyoc/backbox_surrogate_demo_poc

Black-Box Neural Network Replication, Attack, and Defense

Language: Jupyter Notebook - Size: 3.09 MB - Last synced at: 12 days ago - Pushed at: 12 days ago - Stars: 0 - Forks: 0

PACHAKUTlQ/ClaudeCage

Claude Code running in container/sandbox. Packed as single portable executable with no dependency. Better performance than original Claude Code.

Language: Shell - Size: 57.6 KB - Last synced at: 11 days ago - Pushed at: 11 days ago - Stars: 81 - Forks: 3

adhit-r/aran-mcp

Enterprise-Grade MCP (Model Context Protocol) Security and Management Platform

Language: TypeScript - Size: 290 KB - Last synced at: 12 days ago - Pushed at: 15 days ago - Stars: 0 - Forks: 0

alex-ilgayev/MCPSpy

MCP Monitoring with eBPF

Language: C - Size: 6.26 MB - Last synced at: 12 days ago - Pushed at: 13 days ago - Stars: 383 - Forks: 52

wssun/TiSE-CodeLM-Security

This repository provide the studies on the security of language models for code (CodeLMs).

Language: Python - Size: 270 MB - Last synced at: 10 days ago - Pushed at: 6 months ago - Stars: 50 - Forks: 3

SAP/STARS

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.

Language: Python - Size: 2.66 MB - Last synced at: 5 days ago - Pushed at: 6 days ago - Stars: 33 - Forks: 7

Rxcl536/defcon33-model-security-lab

DEF CON 33 AI/ML model security lab explores model serialization vulnerabilities in PyTorch and pickle, demonstrating attack vectors, detection methods, and secure practices. 🐙

Language: Python - Size: 262 KB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 0 - Forks: 0

Abdnour8/HoneyNet-CyberDefense

HoneyNet-CyberDefense 🐙 is an open-source honeypot platform for global cyber defense with AI threat detection, telemetry, and Docker/FastAPI deploy.

Language: Python - Size: 420 KB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 0 - Forks: 0

Atlas-Shield/atlas-shield-spec

Open specification & example policy packs for Atlas Shield to protect AI agents from prompt injection & data exfiltration (MCP-compatible).

Size: 21.5 KB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 0 - Forks: 0

neurons-me/this.env

this.env defines, locks, and hashes the environment to establish a reliable and secure operational context. By detecting and responding to changes, it ensures consistency and integrity, especially for intelligent systems and machine learning applications.

Language: Rust - Size: 147 KB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 58 - Forks: 0

Thiago3584/claude-code-container

🛠️ Run Claude Code effortlessly in a Docker container with "dangerously skip permissions" mode for secure and isolated analysis.

Language: Shell - Size: 16.6 KB - Last synced at: 14 days ago - Pushed at: 15 days ago - Stars: 0 - Forks: 0

reconmap/reconmap

Reconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling end‑to‑end engagement management, from reconnaissance through execution and reporting. With built-in command automation, output parsing, and AI‑assisted summaries, it delivers faster, more structured, and high‑quality security assessments.

Language: HTML - Size: 327 KB - Last synced at: 7 days ago - Pushed at: 2 months ago - Stars: 786 - Forks: 111

Arundhas1212/ai-healthcare-assistant

AI Healthcare Assistant 🐱💻 helps clinicians practice medical communication with AI-driven text and voice feedback using Streamlit and Google Generative AI.

Language: Python - Size: 1.22 MB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 0 - Forks: 0

cyproxio/mcp-for-security

MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workflows.

Language: TypeScript - Size: 247 KB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 347 - Forks: 55

AarambhTech/exam-cheating-detection

AI-powered online exam proctoring system that detects suspicious activities using computer vision. Tracks eye movements, face presence, multiple faces, and talking during exams with real-time alerts and dashboard.

Language: Python - Size: 43 KB - Last synced at: 15 days ago - Pushed at: 4 months ago - Stars: 4 - Forks: 0

HKU-TASR/Imperio

[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.

Language: Python - Size: 2.24 MB - Last synced at: 7 days ago - Pushed at: 7 months ago - Stars: 41 - Forks: 4

pragyabose1011/smart-cctv-yolov8-arcface

Smart CCTV system with YOLOv8 for person detection, ArcFace embeddings for face recognition, and SQLite database logging. Real-time computer vision + deep learning pipeline for intelligent surveillance.

Language: Jupyter Notebook - Size: 425 KB - Last synced at: 17 days ago - Pushed at: 17 days ago - Stars: 0 - Forks: 0

dapurv5/awesome-red-teaming-llms

Repository accompanying the paper https://openreview.net/pdf?id=sSAp8ITBpC

Size: 15 MB - Last synced at: 11 days ago - Pushed at: 18 days ago - Stars: 28 - Forks: 3

Shaziwarits1/AicodeGuard

:octocat: AicodeGuard is a VS Code extension for real-time monitoring of AI coding assistants, detecting implementation gaps, subagent delegation, and blocking planning or deflection.

Language: TypeScript - Size: 172 KB - Last synced at: 20 days ago - Pushed at: 20 days ago - Stars: 0 - Forks: 0

marcellomaugeri/AI-CVE-Analyser

Artifact for the paper "AI-related Vulnerabilities within CVEs: Are We Ready Yet? A Study of Vulnerability Disclosure in AI Products" accepted at AISec'25 co-located with ACM CCS

Language: Python - Size: 9.32 MB - Last synced at: 11 days ago - Pushed at: 24 days ago - Stars: 0 - Forks: 0

dsp-dr/defcon33-model-security-lab

Security research on AI/ML model vulnerabilities based on DEF CON 33 presentations. Demonstrates pickle RCE, TorchScript exploitation, ONNX injection, model poisoning, and integrated LLM attacks with PromptMap2.

Language: Python - Size: 262 KB - Last synced at: 6 days ago - Pushed at: about 1 month ago - Stars: 4 - Forks: 1

edwinkys/phantasm

Toolkits to create a human-in-the-loop approval layer to monitor and guide AI agents workflow in real-time.

Language: Svelte - Size: 782 KB - Last synced at: 14 days ago - Pushed at: 9 months ago - Stars: 179 - Forks: 6

raedmajid/schema-aware-ai-sql-agent

This project enables users to **generate SQL queries from natural language** using **LLM** of their choice while enforcing **Role-Based Access Control (RBAC)** and **Row-Level Security (RLS)**. It also includes **SQL injection detection** and **sensitive data logging** for compliance and security.

Language: Python - Size: 467 KB - Last synced at: 27 days ago - Pushed at: 27 days ago - Stars: 4 - Forks: 0

shahabbaloch101/ai-cloud-security-lab

AI + Cloud Security Labs – A collection of practical CTF challenges and labs focused on AI and cloud security. Covers LLM exploits, SSRF attacks, cloud service abuse, and AI-driven offensive/defensive techniques for hands-on learning and skill building.

Language: Python - Size: 34.2 KB - Last synced at: 27 days ago - Pushed at: 27 days ago - Stars: 0 - Forks: 0

Ali-ihsan-Genis/AI-OS-DESING

Design principles for AI-integrated operating systems, focusing on Linux-based architectures, automation, and security.

Size: 5.86 KB - Last synced at: 28 days ago - Pushed at: 28 days ago - Stars: 0 - Forks: 0

corraith/zkpplatform-core

Strategic foundation for zero-knowledge proof infrastructure. Built for Web3, DeFi, and AI-integrated finance. Privacy-first, compliance-ready, and developer-focused.

Size: 15.6 KB - Last synced at: 29 days ago - Pushed at: 30 days ago - Stars: 0 - Forks: 0

jone0709/Maturity-Model-App

AI Security Maturity Model and assessment toolkit—secure models, data, LLM/RAG, infra, monitoring, and IR across 11 domains and 5 levels, aligned to NIST AI RMF, SAIF, and OWASP LLM Top 10.

Language: TypeScript - Size: 38.1 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

khanovico/prompt-guard

🛡️ Enterprise-grade AI security framework protecting LLMs from prompt injection attacks using ML-powered detection

Language: Python - Size: 5.45 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

llm-platform-security/gpt-data-exposure

An In-Depth Investigation of Data Collection in LLM App Ecosystems

Language: Python - Size: 43.1 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 2 - Forks: 0

rauschecker/AI-Hacking-Challenges

A collection of dockerized hacking challenges that focus on breaking out of AI/LLM security mechanisms.

Language: TypeScript - Size: 284 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 0

slowcoder360/vibesafe

Secure your code in seconds. VibeSafe is an AI-native DevSecOps CLI tool that detects vulnerabilities, secrets, insecure configs, and hallucinated dependencies before they ship.

Language: TypeScript - Size: 205 KB - Last synced at: 23 days ago - Pushed at: 3 months ago - Stars: 20 - Forks: 6

sbeierle/claude4-audit-recon

Recon-Level Audit of Claude 4 – Obfuscated, Ethical & Technically Precise

Language: Python - Size: 27.6 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

GuyNachshon/SocialPsychologyArena

Large-Scale In-Silico Social-Psychology Experiments with LLM Ensembles

Language: Python - Size: 56.6 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

annoeyed/CGRAG

Scalable RAG-based cybersecurity framework for malware detection, anomaly analysis, and CVE intelligence — powered by Qdrant.wered by Qdrant

Language: Python - Size: 3.24 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

utkusen/promptmap

a security scanner for custom LLM applications

Language: Python - Size: 307 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 882 - Forks: 90

f-odc/xai-assisted-intrusion-detection

This repository contains the first resilient Intrusion Detection System that leverages prediction explanations to detect and defend against adversarial attacks on AI-based security models.

Language: Jupyter Notebook - Size: 32.2 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 0

Gersninja/mcp-guard

MCP Guard is an open-source security assessment platform for MCP servers, featuring AIVSS and CVSS v4.0 support. Protect your infrastructure today! 🚀🛡️

Language: Python - Size: 85.9 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

Kansal0920/Emotion-Detection

Next-gen AI-powered Cybersecurity 🔐 | Emotion Detection 🤖 | Voice Alerts 🎙️ | NeuroLock 🧬

Language: Python - Size: 39.1 KB - Last synced at: 28 days ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

trailofbits/pajaMAS

Multi-agent system (MAS) hijacking demos

Language: Python - Size: 21.5 MB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 2 - Forks: 0

sking-dev/sc100-portfolio

End-to-end portfolio for the Microsoft SC-100 Cybersecurity Architect exam - Zero-Trust landing zones, Policy-as-Code, AKS guard-rails, FinOps budget controls, and AI-powered Sentinel playbooks. All projects are IaC-driven (Terraform / Bicep) and mapped directly to the four SC-100 skill domains.

Size: 6.84 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

gopeshkhandelwal/ai-security-labs

Hands-on labs for AI/ML/LLM Security — OWASP Top 10, adversarial attacks, defenses, and red teaming simulations.

Language: Python - Size: 7.81 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

Doleus/doleus

Build confidence in your AI with systematic slice-based testing

Language: Python - Size: 15.6 MB - Last synced at: 8 days ago - Pushed at: 8 days ago - Stars: 11 - Forks: 0

EzgiKorkmaz/adversarial-reinforcement-learning

Reading list for adversarial perspective and robustness in deep reinforcement learning.

Size: 20.5 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 119 - Forks: 7

macawi-ai/macawi-ai

Defensive AI infrastructure using differential topology to absorb attack variety. Building antifragile security systems.

Language: Shell - Size: 138 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

AdirD/prompt-security-node

🚀 Unofficial Node.js SDK for Prompt Security's Protection API.

Language: TypeScript - Size: 394 KB - Last synced at: 20 days ago - Pushed at: 10 months ago - Stars: 6 - Forks: 0

ILDAN2014/llm-fortress

Protect your LLM applications with LLM Fortress, an advanced security firewall that blocks threats and ensures safe operation. 🛡️🚀

Language: Python - Size: 47.9 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

olegnazarov/llm-fortress

Enterprise AI Security Platform - Real-time firewall protection for LLM applications against prompt injection, data leakage, and function abuse attacks

Language: Python - Size: 54.7 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 2 - Forks: 1

Jaelblazer/ai-security-bot

discord-bot ai security monitoring openai python automation

Language: Python - Size: 41 KB - Last synced at: 29 days ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

Balchandar/emcl-protocol

EMCL (Encrypted Model Context Layer): A secure protocol for AI tools with encrypted, signed, identity-aware JSON-RPC calls.

Language: Python - Size: 13.7 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

preambleai/prompt-injector

Comprehensive AI security and compliance testing application.

Language: TypeScript - Size: 516 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0

ishangtxl/VulnPatchAI

An AI-powered vulnerability management platform that automates security assessment and patch prioritization using Google Gemini. This system transforms traditional vulnerability management by parsing Nmap XML scan results and providing intelligent remediation recommendations through NLP.

Language: Python - Size: 488 KB - Last synced at: 15 days ago - Pushed at: 15 days ago - Stars: 2 - Forks: 1

sallysooo/MATCHA_w0r1d

Language: CSS - Size: 34.3 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

gh9869827/fifo-tool-airlock-model-env

Isolated runtime for Hugging Face models requiring `trust_remote_code=True`, using a loopback-only Docker container and a FastAPI bridge.

Language: Python - Size: 144 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 1 - Forks: 0

UsamaMatrix/smart-vuln-automation

⚠️ Description only - code is confidential. AI-powered vulnerability scanner using Nuclei, sqlmap, and FFUF for smart automated assessments.

Size: 4.88 KB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 0 - Forks: 0

LLAMATOR-Core/ai-agents-security

Инициатива, посвященная безопасности агентов на базе искусственного интеллекта

Language: Jupyter Notebook - Size: 42 KB - Last synced at: about 2 months ago - Pushed at: 2 months ago - Stars: 39 - Forks: 6

sking-dev/ai-sec-roadmaps

High-level roadmaps, notes and resources for up-skilling in DevSecOps and AI-powered security.

Size: 19.5 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

AIPwn/awesome-ai-pwn

Size: 10.7 KB - Last synced at: 3 days ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

Gl00ria/AI_4_Dummies

Riding the (AI) wave following the (KISS) principle

Size: 4.88 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

henchiyb/breaker-ai

Breaker AI - Security check for your LLM prompts

Language: TypeScript - Size: 1.06 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 8 - Forks: 1

reds-lab/Narcissus

The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.

Language: Python - Size: 143 KB - Last synced at: about 2 months ago - Pushed at: over 2 years ago - Stars: 118 - Forks: 14

uzaif-lab/E-Gov_Guardian

AI-powered security scanner for web apps & Estonian e-ID smart id and mobile -id

Language: Python - Size: 289 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

firstsnowcg/SwarmPentest

SwarmPentest: World's first open-source multi-agent automated penetration testing framework featuring a blackboard system and plug-in architecture for third-party agent integration, designed for LLM-support.

Language: Python - Size: 376 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 5 - Forks: 2

sbeierle/mistral-downproj-rlhf-patch

Neural patching of Mistral models via MLP.down_proj to bypass RLHF constraints – without touching the LM_HEAD.

Language: HTML - Size: 9.22 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

himanshuh4cker/ai_vulnerability_scanner

AI-powered web vulnerability scanner using stealth payloads and WAF bypass techniques.

Language: Python - Size: 73.2 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

QWEWQ122/TriNetra

TriNetra is a powerful tool for uncovering hidden elements on websites, designed for security professionals and researchers. With its rich output and multi-threaded capabilities, it streamlines the process of finding vulnerabilities and endpoints. 🐙✨

Language: Python - Size: 81.1 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 2 - Forks: 0

lloydpa18/VerifyVision-Pro

VerifyVision-Pro是一个全面的图像伪造篡改检测解决方案，利用深度学习（deep learning）和计算机视觉技术（cv）精确识别各类图像篡改，包括deepfake、AI生成内容、拼接操作和复制-移动篡改。基于PyTorch实现，集成了从数据处理、模型训练到部署的完整工作流程。

Language: Python - Size: 475 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 2 - Forks: 0

EricoPanazzolo/Security-in-LLMs-Validation-of-Risks-in-Simulated-Environments

This repository is part of my final thesis in Computer Science at PUCRS (Brazil). It contains simulated environments for validating security risks in Large Language Models (LLMs), based on the 2025 Top 10 Risk & Mitigations for LLMs and Gen AI Apps (OWASP). Each risk scenario is complete with attack simulations, analysis, and mitigation strategies.

Size: 1.18 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

lechmazur/deception

Benchmark evaluating LLMs on their ability to create and resist disinformation. Includes comprehensive testing across major models (Claude, GPT-4, Gemini, Llama, etc.) with standardized evaluation metrics.

Size: 36.1 KB - Last synced at: about 2 months ago - Pushed at: 6 months ago - Stars: 28 - Forks: 2