#1
berylliumsec/nebulaAI-powered penetration testing assistant that automates reconnaissance, vulnerability analysis, and note-taking via integrated LLMs and CLI tool…
perplexityai/numbatVisibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
luckypipewrench/pipelockOpen-source AI agent firewall that scans HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, emitting verifiable…
samugit83/redamonAutonomous AI red team framework that chains reconnaissance, exploitation, and post-exploitation into a single pipeline, then triages findings,…
pensarai/apex使用自主智能体，直接在您的终端中进行AI驱动的进攻性安全测试。
asgeirtj/system_prompts_leaks从主要AI聊天机器人（包括Claude、ChatGPT、Gemini、Grok和Copilot）中提取的系统提示的精选集合。随着新模型发布定期更新。
mrwadams/attackgenAttackGen 是一款网络安全事件响应测试工具，利用大语言模型的强大能力以及全面的 MITRE ATT&CK 框架。该工具根据用户选择的威胁行为者团体和贵组织的详细信息，生成量身定制的事件响应场景。
reconmap/reconmapReconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling end‑to‑end engagement management, from…
nolabs-ai/nonoagent runtime security - zero trust, zero setup, zero latency agent sandboxing
cisco-ai-defense/defenseclawSecurity Governance for Agentic AI
tencentcloud/cubesandbox面向 AI 智能体的即时、并发、安全且轻量级沙箱。
thalesgroup-cert/watcherAI驱动的威胁情报平台，用于自动化CVE/勒索软件监控、域名监控、数据泄露检测和事件响应，并集成MISP/TheHive。
exploit-garbage/0day-rubbishRedefining vulnerability disclosure in the AI era. We mass-produce exploitable 0days and disclose them directly, using event-driven pressure to…
dmdhrumilmistry/security-harness面向 AI 编码代理的多代理静态应用安全审查框架：映射代码库、搜寻漏洞类别、串联并验证发现结果，并输出 SARIF、JSON 和 PDF 报告。
nvidia/skillspector用于 AI 代理技能的安全扫描器。在安装 Claude Code、Codex 和 MCP 技能之前，检测其中的漏洞、恶意模式、安全风险、提示注入、数据外泄和供应链风险。
xalgorix/xalgorixAutonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.
