Havuz

哥斯拉 MCP 无头版：不启动哥斯拉 GUI，直接用 stdio/HTTP 驱动你的 Webshell（生成马 / 命令执行 / 文件管理），兼容 Claude Desktop、Claude Code、Cursor 等 MCP 客户端。基于 hkdonline/Godzilla-

DianXing - AI-Driven End-to-End Code Security Auditing

Security audit tool for Claude Desktop and Claude Code on macOS — single-command visibility into MCP servers, extensions, plugins, connector

CI-native agent CLI tool for deterministic pipeline gating.

AI protocol scanner — discover exposed MCP servers, A2A Agent Cards, and open LLM APIs in one command. 一条命令盘点 MCP、A2A Agent Card 和 LLM 开放接口暴

The network layer for AI agents. Reach your customers' on-prem data, show what you build, keep it running — through one relay that your mac

An open source, self-hosted, privacy-focused AI workbench

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graph

Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more

Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

pytest for AI agents - Autonomous red-teaming, behavioral monitoring & security testing for LLM agents

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

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Op

🛡 The reference playbook for pentesting AI chatbots & LLM-powered apps in one place. Ready-to-use payloads covering the full OWASP LLM Top 1

AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microsecond latency using CEL

Local security proxy that keeps secrets and sensitive data out of AI requests. Supports Codex, Claude Code and more.

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), dom

Concurrent Go CLI that detects hidden prompt-injection content in documents — invisible Unicode, homoglyphs, hidden HTML, and known trigger

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

The AI Autonomous SOC & Purple-Team Engine

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.

An open library of 206 security skills for AI agents — pentest, bug bounty, CTF, reversing & defense across 23 domains, with CI-verified rou

The autonomous pentester that proves its findings — AI-driven, evidence-first, behind-login.

Open-source runtime security and execution control for autonomous AI agents. ALLOW, BLOCK, ESCALATE at the execution boundary with auditable

Praxis Policy Engine (PPE)

A Claude / AI security review prompt for shipping safe apps. TRAP (True Readiness Audit Prompt) turns Claude Code, Cursor, or Copilot into a

Security scanner for AI agent skills. Flags known prompt-injection, data-exfiltration and malicious-payload patterns before you install

📜🦀🌐 Intelligent, Secure and Effortless Super Full-Stack Framework 🌐🦀📜"Rust for those who want to build securely and easily, but not suffer"

Ground truth for enterprise AI: your AI coding tools, your accounts and every session on your own server, from one web console, CLI or API.

Open-source config scanner for AI coding agents: scores the permissions, hooks, sandbox and MCP settings of Claude Code, Codex, Cursor and G

Trust & security scanner for AI agents and MCP servers — OWASP-mapped findings, Trust Cards (A–F grades), SARIF + CI gate. Free CLI, zero te

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-bound

Open-source adversary emulation for AI agents and MCP servers.

A privacy-first AI agent that sanitizes your prompts locally with a local LLM before forwarding to remote LLM APIs.

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.

Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare, and review locally; continue in the ClearFrame CLI or Mac app

Policy-aware static taint analysis for detecting sensitive-data flows into LLM APIs.

Universal AI Charter: plain-language governance principles and a public certification registry for AI models, built on disclosure instead of

Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: an

Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.

👻 AI-Powered Pentesting Command Center — Autonomous security testing with real-time streaming, self-improving AI, unlimited tool iterations,

Security-oriented three-axis observability for sandboxed AI agents: model intent, app context, and runtime telemetry into verifiable evidenc

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.