Havuz

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

Evidence-grounded AI secretary for Claude Code and Codex, with frozen context, deterministic retrieval, bounded quality review, and explicit

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

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

rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catc

Research artifacts for provenance-bound agent authorization, signed effect evidence, and reproducible security evaluation.

AI SRE agent diagnosing Kubernetes incidents over Google Chat — security-first sandbox: NixOS VM, default-deny egress, hard tool denylist ag

Privacy and security guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and tool authorization

Document extraction and validation for logistics companies.

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

Lightweight, agent-friendly AI security toolkit for Node.js & TypeScript. Check if your agent has loaded the skill, Stop prompt injection, a

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

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

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for

🛡️ Runtime guardrails for AI agents. Intercept and block unsafe tool calls caused by prompt injection.

BloodHound-style risk analysis for multi-agent AI architectures. Parses CrewAI, Dify, LangGraph, or generic YAML into a typed capability gra

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loa

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI pe

FinSecAI: An experimental testbed for evaluating Prompt Injection, Jailbreak, and data extraction vulnerabilities in financial LLM agents vi

Context bomb strings

Default-deny MCP/JSON-RPC security gateway for agent tool-call authorization, prompt-injection detection, exfiltration controls, and audit t

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

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

Deterministic security analysis for agent skill files.

OpenGuardrailsBench (OGB): an open, reproducible benchmark for AI guardrails across safety, security, privacy and policy

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

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAG

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

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

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model

Security-First Agentic IDE Coding Harness

Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial

A modular, drop-in middleware collection for Laravel AI SDK agents. Offers middleware across security, observability, performance and guidan

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

Runtime security for AI agents. In-process, zero dependencies, Apache 2.0.

Static security scanner for npm/PyPI packages, MCP servers, agent skills and repos. Runs locally, never runs the code, no LLM. CLI, Claude C

Crash-test insurance claim AI agents before production.

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate signer; the model ne

Zero-Trust Semantic Scraper & Firewall Proxy for AI Coding Agents. Intercepts and neutralizes web-scraped prompt injections locally before t

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt i

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

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

OpenAI Codex 自定义系统提示词注入工具 | System Prompt Injection | CTF Security Research Red Team | Auto Install | Cross-Platform

Self-hosted LLM gateway that turns flat-rate AI subscriptions (Claude Code Max, ChatGPT Plus, Codex, Copilot, M365, Gemini) into one OpenAI/

Free security skills for AI-built apps — run /lictor-security-check in Claude Code before you ship. Plain English, read-only, no telemetry.

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif

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