vulnerability-discovery

Discovering vulnerabilities in firmware through concolic analysis and function clustering.

漏洞挖掘神器 | 浏览器插件 | 发现页面和JS中的隐藏接口和敏感信息、URL批量打开 & Vulnerability Mining Tool | Browser Plugin | Discover Hidden Interfaces, Sensitive Information in Pages and JS, Open Multiple URLs | Notepad

A Binary Ninja plugin using backward slicing of variables as a driver for static taint analysis

A project that uses Binary Ninja and GRAKN.AI to perform static analysis on binary files with the goal of identifying bugs in software.

AI 驱动的自主渗透测试平台：输入目标，AI agent 自动完成侦察→规划→主动测试→漏洞验证→报告生成。黑板引擎+多 worker+SRC 验收门禁。仅供学术与安全研究使用。

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Opus 4.7. Eight-phase sink-guided pipeline, ~$1/run, OSS self-scan and coordinated disclosure.

This search engine automates the discovery of sensitive information using customized dorks across GitHub, Google, and Shodan.

Mythos-class autonomous vulnerability discovery from any strong coding model (Opus 4.7, GPT-5.5, DeepSeek V4, Gemini). Long-running, email-driven, self-distills skills, mutates its own code.

基于 pi 的渗透测试 / SRC 漏洞挖掘 Agent：确定性信息收集 + LLM 编排挖洞 + 漏洞复审 + Vue3 Web 指挥台

A collection of security research papers, tools about monolithic firmware.

Multi-agent vulnerability discovery pipeline following the Project Glasswing / Cloudflare methodology. Hunt, validate, dedupe, trace, and POC vulnerabilities at scale with LLM agents.

PHP/Java/Python/Go/.NET 多语言代码审计 Codex Skill：Source-to-Sink、PoC、修复建议、CNVD/CVE 提交型报告

FirmHound 固件猎犬：IoT 固件漏洞挖掘自动化流水线（挑战杯揭榜挂帅·网络安全赛题第一队作品）。解包→攻击面→二进制分析→静态审计→十维评分→反证验证→动态验证→证据报告。

High-performance, baseline-aware fuzzing and vulnerability discovery framework for multi-target security testing, with adaptive mutation, coverage feedback, corpus management, crash detection, minimization, structured evidence, and reproducible fuzzing campaigns.

This repository contains the source code for our paper "Broken Promises: Measuring Confounding Effects in Learning-based Vulnerability Discovery" that was accepted at AISec '23.

授权安全测试技能库：Tri-Ring 三环并行编排（广度发现 / 深度攻击 / 创造探索 + 仲裁门控）× 四端分仓（Claude Code / Codex / opencode / Pi），31 个主干 skill + 187 个上游方法论弹药库，内置 CNVD/EduSRC 报告模板与提交前证据门禁

Resource repository for Mole

An AI-augmented hybrid fuzzer built on AFL++ to bypass validity barriers in structured parsers. By feeding AFL++ with structurally valid inputs generated via local AI, it penetrates initial validation layers to uncover deep-logic, real-world bugs under a responsible disclosure framework.

三环并行渗透测试 dsh 插件 — discovery/deep/creative 三环 + 独立 verify 闭环，Kuzu 图黑板共享状态，多 agent 自调度、按角色模型策略、自学习知识脑。仅用于授权安全测试（SRC/靶场/自有资产）。