代码编程与辅助分类精选
AI 安全
安全测试、行为约束与高合规运行保障
工具列表
13 个工具Astra
强调数据隐私隔离的 AI Agent 构建与运行平台
Astra Security
面向网站和应用的 AI 辅助安全扫描与渗透测试平台
ElevenAgents Guardrails 2.0
ElevenAgents 语音智能体的可配置安全控制层
CyberStrikeAI
CyberStrikeAI 是 GitHub 开源项目，仓库摘要为：AI-native security testing platform with multi-tool orchestration
WinClaw
面向高安全与强合规场景的桌面级 AI 智能体平台
DCP
为 AI Agent 提供加密权限、密钥和访问控制的安全层
AboutSecurity
AboutSecurity 是 GitHub 开源项目，仓库摘要为：Everything for pentest. | 渗透测试知识库，以 AI Agent 可执行的格式沉淀安全方法论
everything-claude-code
everything-claude-code 是 GitHub 开源项目，仓库摘要为：The agent harness performance optimization system. Skills, instincts, memory, security, and research-first
agentshield
agentshield 是 GitHub 开源项目，仓库摘要为：AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permission
promptfoo
promptfoo 是 GitHub 开源项目，仓库摘要为：Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performa
pentest-ai
pentest-ai 是 GitHub 开源项目，仓库摘要为：Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWA
ironclaw
ironclaw 是 GitHub 开源项目，仓库摘要为：IronClaw is an Agent OS focused on privacy, security and extensibility
PyRIT
PyRIT 是 GitHub 开源项目，仓库摘要为：The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower