InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. 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

    Stale GitHub, Baimuking 75 ★Custom licence (see repository)Updated 28 days ago

    git clone https://github.com/Baimuking/AI-Jailbreak.git
  2. 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

    Stale GitHub, WestFox-AwA 146 ★BSD-3-ClauseUpdated 9 days ago

    git clone https://github.com/WestFox-AwA/dsh-wish-specializer.git
  3. skylos

    Agents & frameworks

    Open 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/

    Indexed GitHub, duriantaco 944 ★Apache-2.0Updated yesterday

    git clone https://github.com/duriantaco/skylos.git
  4. A curated corpus of incidents, attack vectors, failure modes, and defensive tools for autonomous AI agents.

    Stale GitHub, h5i-dev 57 ★MITUpdated 32 days ago

    git clone https://github.com/h5i-dev/awesome-ai-agent-incidents.git
  5. Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.

    Indexed GitHub, OWASP 204 ★Apache-2.0Updated yesterday

    git clone https://github.com/OWASP/www-project-agent-memory-guard.git
  6. Browser 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.

    Indexed GitHub, OMD-123 13 ★MITUpdated 2 days ago

    git clone https://github.com/OMD-123/browser-verified-skill.git
  7. mu

    Agents & frameworks

    mu (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.

    Indexed GitHub, qybaihe 607 ★MITUpdated yesterday

    git clone https://github.com/qybaihe/mu.git
  8. guardana

    MCP servers

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

    Indexed GitHub, guardana 225 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/guardana/guardana.git
  9. New updated extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

    Stale GitHub, zebbern 30 ★Updated 16 months ago

    git clone https://github.com/zebbern/system_prompts_leaks.git
  10. tenuo

    Agents & frameworks

    Task-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.

    Stale GitHub, tenuo-ai 106 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/tenuo-ai/tenuo.git
  11. A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-teaming, and defensive hardening.

    Indexed GitHub, e2sy 102 ★MITUpdated today

    git clone https://github.com/e2sy/jailbreak-archives.git
  12. pic-standard

    MCP servers

    Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.

    Stale GitHub, pic-standard 70 ★Apache-2.0Updated 10 days ago

    git clone https://github.com/pic-standard/pic-standard.git
  13. 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.

    Stale GitHub, graygnatconsole 543 ★MITUpdated 23 days ago

    git clone https://github.com/graygnatconsole/mcp-audit-tool.git
  14. Mcpwn

    MCP servers

    Automated security scanner for Model Context Protocol servers that detects RCE, path traversal, prompt injection, and protocol vulnerabilities.

    Stale GitHub, Teycir 31 ★MITUpdated 31 days ago

    git clone https://github.com/Teycir/Mcpwn.git
  15. ShibaClaw

    Agents & frameworks

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

    Indexed GitHub, RikyZ90 85 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/RikyZ90/ShibaClaw.git
  16. ave

    MCP servers

    AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.

    Stale GitHub, aveproject 24 ★Apache-2.0Updated 17 days ago

    git clone https://github.com/aveproject/ave.git
  17. 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

    Stale GitHub, heaven999b 187 ★MITUpdated 49 days ago

    git clone https://github.com/heaven999b/hello-agent-system.git
  18. mastyf.ai

    MCP servers

    Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial testing, and real-time threat detection.

    Stale GitHub, mastyf-ai 21 ★AGPL-3.0Updated 9 days ago

    git clone https://github.com/mastyf-ai/mastyf.ai.git
  19. An open database of real-world AI agent incidents.

    Stale GitHub, Continuum-AI-Corp 30 ★Custom licence (see repository)Updated 7 days ago

    git clone https://github.com/Continuum-AI-Corp/Orca-AI-Incident-Archive.git
  20. node9-proxy

    Agents & frameworks

    Access 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.

    Indexed GitHub, node9-ai 225 ★Apache-2.0Updated yesterday

    git clone https://github.com/node9-ai/node9-proxy.git
  21. Argus

    Agents & frameworks

    Open-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.

    Indexed GitHub, gy15901580825 210 ★Apache-2.0Updated today

    git clone https://github.com/gy15901580825/Argus.git
  22. cfgaudit

    MCP servers

    Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. SARIF output, OWASP LLM Top 10 mapping.

    Indexed GitHub, cfgaudit 27 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/cfgaudit/cfgaudit.git
  23. OpenART

    Skills

    OpenART 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.

    Stale GitHub, AI45Lab 263 ★AGPL-3.0Updated 15 days ago

    git clone https://github.com/AI45Lab/OpenART.git
  24. 5,660 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.

    Stale GitHub, AnthonyHerman 8 ★CC-BY-4.0Updated 5 days ago

    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.