Stars
让你的命令行 Agent 在后台自己接活、自己跟进到底；平时不烦你，遇到拿不准的事才发卡片找你拍板。
Tiny metrics client for worker processes
[Usenix Security 2026] Policy-Aware Security Auditing for Mobile Agents
This repository is designed to automate the detection and cleanup of in-memory web shells using MCP in combination with the memory-shell-detector tool. / 本仓库旨在结合 MCP 与 memory-shell-detector 工具，实现对内…
Phobos 是一款红队专用免杀木马生成器，采用 PEM 加密动态嵌入 XOR 的方式生成木马，生成木马可以自定义名称和ICO图标，为了延长免杀时间本工具暂时不开源。
Single-binary intranet scanner in Go: host discovery, port scan, web title, 387 embedded PoC rules, weak-credential brute force for 11 protocols.
Zack-BypassWeb是可一键生成适配冰蝎4.1的 JSP / JSPX / PHP / ASP / ASPX / ASHX 六种 Webshell，内置 15 种以上的代码混淆与免杀技术，在保证冰蝎正常连接的前提下，最大程度规避主流安全产品的查杀。
A Burp Suite extension that puts an LLM-driven vulnerability scan behind a right-click — or behind Proxy auto-scan (off by default), which turns parameterised proxy traffic into scan tasks. The mod…
Next Generation C2 Framework, IoM-server/client
Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Qwen Code, iFlow as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 2.5 Pro, GPT 5, Claude, Qwe…
AlterHive（幻巢）是一款面向攻防演练、红蓝对抗和安全研究场景的高交互智能欺骗蜜罐平台。平台以虚拟拓扑、会话记忆、规则引擎和多 Agent 欺骗规划为核心，将攻击者/渗透Agent引导进可控的“子网幻象”环境中，帮助防守方观察攻击意图、拖延攻击节奏、保护真实目标。
通过网页内容逐步诱导AI系统执行恶意指令，最终建立反向Shell连接的Exp
面向移动安全分析场景的 6 阶段总控 Skill。用于统一调度 APK 静态侦察、流量与代码对齐、SO/JNI 深度分析、加密与漏洞综合分析、验证设计与报告交付流程。支持 JADX MCP、Burp/Yakit MCP、IDA/Ghidra MCP。
结合chrome-devtools-mcp的能力并加上Skill的规范，实现JSRPC+Flask+autoDecoder方案的前端JS逆向自动化分析，提升JS逆向的效率
EFF-Monitoring是一款面向安全运营场景的告警协作与 AI 研判平台。平台围绕安全事件全生命周期，提供AI研判、处置流转、经验沉淀、插件接入等能力，通过证据驱动的分析与协同机制，帮助安全团队快速看懂告警、定位风险、联动上下游并提升处置效率。
Pentest AI agents: 23 hunt-agent skills, a 4-arm detection engine, a 14-gate validation lab, and the two gates that stop false findings in both directions.
Agentic command-and-control system for autonomous network propagation
AI Agent 驱动的移动端逆向技能集：Frida hook、一键脱壳、反检测绕过、内存 DEX dump、Ghidra MCP 符号/结构恢复。AI-agent skill system for mobile reverse engineering.
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise ide…
Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound …
Craft Anything: understand how any software works, and craft your own.
An intelligent reverse engineering and AI-assisted analysis tool for HarmonyOS NEXT (HAP/APP/ABC), Android (APK/AAB), iOS (IPA), and native PE/ELF/Mach-O binaries.