
nuguard
opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

opensource repo for validating agentic AI applications: redteam, behavior, supply-chain, static analysis

Static analysis CLI that scans codebases for LLM prompt-injection, data-exfiltration, jailbreak, and unsafe agent/tool vulnerabilities. Runs fully…

AI-Assisted Reverse Engineering with Ghidra

Android deeplink misconfiguration detector and exploitation tool

100% Free & Open Source • Privacy-First Security Scanning and AI Code Review CLI

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Self-hosted multi-agent environment for Go with LLM-powered pentesting agents (exploiter, reverser, threathunter, webscanner) that automate…

Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

Scan a repo's .claude/ config (settings.json hooks, MCP servers, env, allowed-tools) for the RCE & API-key-exfiltration footguns (CVE-2025-59536,…

Ensemble framework for software vulnerability detection and repair using multiple large language models, with consensus analysis and evaluation tools…

Technical analysis of the LangChain serialization injection vulnerability CVE-2025-68664.

Study of CVE-2018-6341 in React, demonstrating AI-assisted vulnerability detection, root-cause analysis, and remediation guidance for JavaScript…

DeepAudit:人人拥有的 AI 黑客战队,让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行,自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ,一键生成报告。支持中转站。让安全不再昂贵,让审计不再复杂。

A minimal, secure Python interpreter written in Rust for use by AI

A GitHub Action invoking the Gemini CLI.

Security Governance for Agentic AI

AI-powered Docker security scanner that explains vulnerabilities in plain English. An OWASP Lab Project.

a guard that blocks catastrophic agent actions