Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
AI-Jailbreak
Prompts全网最全的 AI 破甲合集:一个仓库破甲所有模型。收录 1733 个上游破甲项目,9 条可一键安装的破甲卡覆盖 GPT/Claude/Gemini/DeepSeek/GLM/Kimi/Grok/Qwen 与本地模型,内置 llms.txt 让 Claude Code/Codex/Cursor 自己装 有用的话可以点个收藏星星,会持续收录
git clone https://github.com/Baimuking/AI-Jailbreak.git -
dsh-wish-specializer
Prompts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
git clone https://github.com/WestFox-AwA/dsh-wish-specializer.git -
skylos
Agents & frameworksOpen source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistakes before merge. For first timers refer to https://duriantaco.github.io/skylos/repo-map/
git clone https://github.com/duriantaco/skylos.git -
awesome-ai-agent-incidents
SkillsA curated corpus of incidents, attack vectors, failure modes, and defensive tools for autonomous AI agents.
git clone https://github.com/h5i-dev/awesome-ai-agent-incidents.git -
www-project-agent-memory-guard
MCP serversRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
git clone https://github.com/OWASP/www-project-agent-memory-guard.git -
browser-verified-skill
SkillsBrowser automation with evidence. An Agent Skill that lets an AI agent drive a real browser while every action passes a policy gate, every run leaves an auditable artifact, and the run compiles into a plain Playwright script that replays for free.
git clone https://github.com/OMD-123/browser-verified-skill.git -
mu
Agents & frameworksmu (μ): most of what a coding agent decides isn't code. mu hands 40 kinds of yes/no calls to a small model: fewer wasted tokens, fewer approvals on autopilot, fewer runs that stop halfway. Built on pi.
git clone https://github.com/qybaihe/mu.git -
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.git -
system_prompts_leaks
PromptsNew updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini
git clone https://github.com/zebbern/system_prompts_leaks.git -
tenuo
Agents & frameworksTask-scoped authorization for AI agents. Cryptographic warrants constrain tools and arguments, prevent privilege escalation at every delegation hop, and produce signed evidence of what was allowed or denied.
git clone https://github.com/tenuo-ai/tenuo.git -
jailbreak-archives
PromptsA structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.
git clone https://github.com/e2sy/jailbreak-archives.git -
pic-standard
MCP serversOpen standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
git clone https://github.com/pic-standard/pic-standard.git -
mcp-audit-tool
MCP servers🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.
git clone https://github.com/graygnatconsole/mcp-audit-tool.git -
Mcpwn
MCP serversAutomated security scanner for Model Context Protocol servers that detects RCE, path traversal, prompt injection, and protocol vulnerabilities.
git clone https://github.com/Teycir/Mcpwn.git -
ShibaClaw
Agents & frameworksSelf-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.
git clone https://github.com/RikyZ90/ShibaClaw.git -
ave
MCP serversAVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
git clone https://github.com/aveproject/ave.git -
hello-agent-system
Docs & tutorials👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营
git clone https://github.com/heaven999b/hello-agent-system.git -
mastyf.ai
MCP serversOpen-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.
git clone https://github.com/mastyf-ai/mastyf.ai.git -
Orca-AI-Incident-Archive
MCP serversAn open database of real-world AI agent incidents.
git clone https://github.com/Continuum-AI-Corp/Orca-AI-Incident-Archive.git -
node9-proxy
Agents & frameworksAccess control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
git clone https://github.com/node9-ai/node9-proxy.git -
Argus
Agents & frameworksOpen-source red-team testing for AI agents. 266 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.
git clone https://github.com/gy15901580825/Argus.git -
cfgaudit
MCP serversStatic security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, OWASP LLM Top 10 mapping.
git clone https://github.com/cfgaudit/cfgaudit.git -
OpenART
SkillsOpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios.
git clone https://github.com/AI45Lab/OpenART.git -
ai-security-corpus
Skills5,660 AI security links: prompt injection, LLM & AI agent security, MCP, coding agents, agent skills & supply chain, red teaming, guardrails, sandboxing, incidents & CVEs, governance. 570 arXiv papers, 1,155 GitHub repos, 570 X posts, 29 categories of plain markdown you can grep, diff and fork. Obsidian vault export. Added, not endorsed.
git clone https://github.com/AnthonyHerman/ai-security-corpus.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.