Havuz

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

Agents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a t

Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for pr

破甲next · macOS 版 | WorkBuddy + Codex 人格注入装载台（WorkBuddy 六层靶点 / Codex 双锚点 + 封条完整性保护 + 反去标识化声明）。纯 Python 标准库 + Bash，零第三方依赖、零网络请求、改前自动备份、随时一键还原。

Security scanner for MCP servers, source trees, and packages, with explicit findings and coverage reporting.

Chinese-first LLM jailbreak benchmark & red-team toolkit | 中文LLM安全评测框架 | by POJIA.AI

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Repro

mu, coding agent kararlarının bir kısmını küçük bir judge modeline devrederek pi tabanlı CLI ve desktop agent sunar.

Neden yükseliyor · 14 günlük yaşına rağmen 386 yıldız, son 28 günde 731 commit ve 11 farklı yazar raporlanıyor; bu kısa sürede dikkat ve geliştirme hareketliliğine işaret ediyor. Ancak bu veriler kalıcı benimseme veya üretim olgunluğunu tek başına kanıtlamıyor.

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F

Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside Deep

An open database of real-world AI agent incidents.

Command-line tool for TypeSafe's Jev AI model

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

三个 AI 客户端的内置提示词一键替换：DSH / WorkBuddy / ZCode。双击即用、可自证、改前备份、一键还原。v8.29：卡片式界面、登录强制激活码、DSH 插件自动注入、官方群验证。免装 Python 单文件 exe，完全免费开源。

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injectio

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

Sentinel shows what a file would make your AI coding agent do. Static analyzer, merge gate and signed lockfile for CLAUDE.md, AGENTS.md, .cu

Claude skill that catches hidden prompt-injection text in documents before acting on them

Agent Canary 3.0: open-source MCP, SDK, and CLI security toolkit with a guarded execution gateway, decoy signals, local tests, and public ac

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

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

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

Zero-dependency guardrail framework for AI agents. Stops runaway loops, prompt injection, hallucination and unsafe tool calls before they ex

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

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten

A Collection of Defensive Cyber Security skills designed to harden your Software, Infrastructure and even Game.

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk

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

A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

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

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

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

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