Havuz

Hermes Agent (NousResearch) sandboxed by NVIDIA OpenShell — hardware-enforced network/filesystem/syscall policy, full memory + gateway stack

Prompt-injection, jailbreak and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanit

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Scan Python dependencies for exploited CVEs and abandoned packages that handle untrusted input, ranked by CISA KEV and EPSS. Runs in CI and

The agent that writes the code never reviews it. Spec-driven TDD with agent separation, adversarial QA, and dynamic rigor for Claude Code.

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation,

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

All-in-one open-source framework & middleware for enterprise-grade multi-tenant and multi-tier XaaS Services development

Luvv-MCP 是一个 AI 原生的前端安全分析引擎，接入 Claude Code 后，你说一句"帮我审计这个网站"，AI 就能自动完成技术栈识别（1.8 万条规则覆盖 CMS/框架/CDN/中间件）、泄露扫描（阿里云 AK、GitHub Token、Webhook、J

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a clien

AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy,

AiGuard —— 本地优先的 AI 流量安全网关：本机 MITM 代理只接管 AI 域名，请求侧脱敏、响应侧流式还原，并识别七类风险信号。原文不落盘、不上传。（注意如果你需要模型直接使用token或者其他密钥进行操作，请放入白名单或关闭该功能！！！！）

Find what's using a port, who started it (Claude Code, Cursor, Docker…), whether your network can reach it, and stop it safely. An lsof alte

Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens the fix PR. CLI, GitHub Action, or scheduled

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Hands-off supply-chain watchdog for dev machines: orchestrates multiple security scanners (Perplexity bumblebee + osv-scanner, govulncheck,

A curated collection of AI SecOps 24 SKILL.md capabilities for security work offensive security, SOC and detection engineering, cloud and Ku

Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory,

Secrets management for AI agents: approve API keys and credentials on your phone with biometrics, delivered end-to-end encrypted into the ta

Find and fix web-app vulnerabilities in one command — SAST + DAST + AI, for devs who aren't security experts.

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Every way an LLM can break one SDK to stop it. Injection. Hallucination. Leakage. Handled.

A secure way to run enterprise AI agents. Building blocks with per-action authorization, prompt-injection containment, least privilege, and

Experimental source-available SQLite/libSQL backend for human-and-agent-native workflows, with Studio and scoped MCP access.

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e

CLI for Local Isolated Environments for Coding Agents

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalat

The AI security agent guards your code.

Solana's SOL-0XX security standard — bug-class rules distilled from $514M of real exploits, firing as you code in every AI tool, editor & CI

Praxis Policy Engine (PPE)

Advanced pentest & BadUSB toolkit for the LILYGO T-Dongle-S3 (ESP32-S3 Device) HID, Deauth, EvilAP, MCP AI and more - Web Flasher Online

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

Your AI agent needs your API keys. It doesn't need to see them. tokenstash writes keys straight into .env.local for Claude Code, Codex, Curs

Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a fo

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

Session-scoped GPT-5.6 agent routing for Claude Code

Agent-assisted vulnerability research across Rust, Android APKs, and AI agents: independent discovery, skeptical triage, verification, and p

Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys

An accelerator that reviews a Microsoft Fabric tenant end-to-end through metadata-only scans across governance, cost, capacity, performance,

Real-time data anonymization for LLMs: secure your logs and conversations across cloud or local environments. Docker-ready & Multi-IA suppor

The AI-operated escrow court and reputation protocol for the agentic economy.

Read-only Telegram MCP server. Search chats, read messages, and download attachments from any MCP client.

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol server

Browser extension with 35+ rules for keeping your AI agent safe while browsing

Pre-production checklists for solo founders. 4,685 items, 88% portable to any stack, 26 stack supplements — plus AI/agent security and the b