Havuz

Context bomb strings

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

A vendor-neutral collection of Sigma, YARA, and Suricata rules for detecting compromise of LLM applications, MCP servers, ML supply chains,

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

OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and TOTP while keeping hidden plaint

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

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

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

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

Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every release.

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.

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

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.

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

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

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

LLM-native static vulnerability detection: point it at a repo and get a reviewable vuln report, the way a human auditor would.

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

🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua

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

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.

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve

Executable security regression testing for agentic applications and MCP-integrated systems.

sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nod

AI agent benchmark hackability scanner — find evaluation vulnerabilities before they undermine your results

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a

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

Local-first MCP security scanner for AI-generated apps: four open-source engines plus the Synvoya engine. Scan → fix → rescan from Claude Co

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

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

Protecting digital communications against audio deepfakes with real-time AI. This system analyzes audio streams to detect synthesized voices

Autonomous AI-powered penetration testing platform. LLM-driven recon, vulnerability analysis, and exploit validation for internal & external

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

See how you really use AI — X-ray your AI coding sessions locally

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

250+ real-world TypeScript AI projects: workflows, agents, and multi-agent systems with production-ready architecture, not chatbot demos.

Self-hosted LLM security proxy. PII redaction, prompt injection defense, KVKK/GDPR/PCI-DSS compliance. Sub-millisecond latency

Public SDKs and integration contracts for Armorer Guard.

reconnaissance for agent attack surfaces

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

RAG pipeline security testing toolkit - 27 techniques across 6 kill chain phases, mapped to MITRE ATLAS

Verify which LLM an OpenAI-compatible API really serves — single-token behavioral fingerprinting (Jensen-Shannon) from the paper "One Token

Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref

🛡 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