CanoP
openbreach/canop静态分析CLI，用于扫描AI生成的代码中的漏洞，如SQL注入、不安全反射和硬编码密钥，并支持SARIF导出和CI/CD门禁。
defensive-toolsstatic-analysisvulnerability-scanners+7
gmh5225/enigma-Ghidra 分析核心的 C++ 重新实现，不依赖 JVM，提供可嵌入的二进制分析、Pcode/Sleigh 基础以及面向逆向工程的 AI 就绪接口。
gavmor/x86-cpp-reversing-skill用于逆向工程32位小端x86 C++二进制文件（虚表、RTTI、继承关系恢复）的Claude Code技能
owasp/trisuella-aidlca-frameworkPolicy-governed LLMSecOps framework providing AST-based SAST, secret scanning, supply-chain and multi-cloud CSPM checks, AI-BoM generation, and CI/CD…
owasp-noir/alibiCross-check the views of your attack surface and find the endpoints that cannot corroborate each other.
martian56/redcellAI 红队平台。自主 LLM 智能体在 Kali 容器内端到端执行渗透测试并撰写报告。LangGraph 计划/执行引擎，通过 LiteLLM 实现提供商无关的模型，输出 PDF/JSON/SARIF。FastAPI + React。
offensive360/sast-scan-actionGitHub Action for Offensive360 SAST scans and SARIF results. See the open-source program for eligibility and setup.
offensive360/mcp-serverMCP 服务器，可在本地代码库上运行 SAST 扫描，并返回带有严重级别和修复建议的发现结果，使 AI 助手能够执行安全分析和修复。
lgranadoi/sift-hardened# 针对 CVE-2026-85625 的 sift 17.1.3 安全加固分支。与 crcn/sift.js 无关联。
soemoescode/guardskillRead-only scanner for what lets a repository run code in a coding agent (Claude Code, Codex, Cursor, Copilot): git settings, hooks, and committed MCP…
safeagent-beihang/clawguardEnterprise AI agent security toolkit providing pre-flight auditing, configuration hardening, runtime threat detection, and active defense against…
geeksikhsecurity/ai-tool-poisoning-guardFree security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…
iamavu/zairoScans code diffs with context to build an impact graph and uses LLMs to find vulnerabilities, supporting multi-repo scans and CI gating with SARIF…
dannydoodlesstory/evm-audit-helpers智能合约安全审计的 Solidity 代码片段与 Foundry 脚本合集
javascript-obfuscator/javascript-obfuscator混淆JavaScript和Node.js代码，通过变量重命名、字符串加密、控制流扁平化和反调试技术，保护源代码免受逆向工程。