Havuz

iFixAi, AI agent’ları yapılandırılabilir testler ve model judge’larıyla denetleyip puan kartı ve raporlar üreten bir Python aracıdır.

Neden yükseliyor · 153 günlük bir depoda 15.702 yıldız ve son 28 günde 9 commit ile 5 farklı yazar görünmesi güçlü ilgiye ve devam eden katkıya işaret ediyor. README’de birden fazla kullanım yolu ve agent ekosistemi entegrasyonları öne çıkarılıyor; ancak yıldızlar ürün kalitesini veya değerlendirmelerin doğruluğunu kanıtlamaz.

SkillSpector, AI agent skills paketlerini yüklemeden önce güvenlik riskleri açısından tarayan bir Python aracıdır.

Neden yükseliyor · AI agent skills ekosistemindeki güvenlik ihtiyacına doğrudan yanıt veriyor ve NVIDIA Verified Skills pipeline'ıyla bağlantılı. 191 günlük bir repo için 18.391 yıldızın yanı sıra son 28 günde 144 commit ve 24 farklı yazar, dikkat çekmenin yalnızca README iddialarına dayanmadığını gösteriyor.

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。

ADR, AI agent’ları keşfetmek, etkinliklerini gözlemlemek ve riskli davranışları tespit etmek için araçlar ile benchmark’lar sunan açık kaynaklı bir güvenlik sistemidir.

Neden yükseliyor · AI agent güvenliği güncel ve kurumsal ölçekte büyüyen bir ihtiyaç; Uber’in projeyi açık kaynak olarak yayımlaması, README’de üretimde kullanıldığını ve MLSys 2026’da kabul edilen bir makaleyle desteklendiğini belirtmesi ilgiyi artırıyor. 167 günde 1.620 yıldızın yanı sıra son 28 gündeki 44 commit ve 15 farklı yazar, kayda değer proje etkinliğine işaret ediyor; ancak yıldız geçmişi olmadan yükseliş hızını doğrulamak mümkün değil.

Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugi

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, er

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

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

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

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

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

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

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

AutoHarness: Automated Harness Engineering for AI Agents

Deterministic safety solutions for probabilistic AI agents

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

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

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

Context bomb strings

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

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

从 165 个顶级 AI 产品系统提示词中蒸馏出的 15 个可执行 Agent skill

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

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

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

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

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

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

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

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

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

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

Command-line tool for TypeSafe's Jev AI model

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

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

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

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

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

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

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

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

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

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

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

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

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

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

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

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

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation