InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. superagent

    AI repositories

    Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

    Stale GitHub, superagent-ai 6,763 ★MITUpdated 2 months ago

    git clone https://github.com/superagent-ai/superagent.git
  2. SkillSpector

    Skills

    Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

    Indexed GitHub, NVIDIA 25.9k ★Apache-2.0Updated 2 days ago

    git clone https://github.com/NVIDIA/SkillSpector.git
  3. prompt-injections

    Datasets & benchmarks

    Hugging Face dataset by deepset

    Stale Hugging Face Hub, deepset 188 ♥apache-2.0Updated 2 years ago

    deepset/prompt-injections
  4. prompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记

    Stale GitHub, yunwei37 368 ★MITUpdated 20 months ago

    git clone https://github.com/yunwei37/prompt-hacker-collections.git
  5. promptmap

    Prompts

    a security scanner for custom LLM applications

    Stale GitHub, utkusen 1,281 ★GPL-3.0Updated 11 months ago

    git clone https://github.com/utkusen/promptmap.git
  6. AISafetyHot

    MCP servers

    AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.

    Indexed GitHub, wuyoscar 2,127 ★Custom licence (see repository)Updated today

    git clone https://github.com/wuyoscar/AISafetyHot.git
  7. A collection of GPT system prompts and various prompt injection/leaking knowledge.

    Stale GitHub, LouisShark 10.8k ★MITUpdated 7 days ago

    git clone https://github.com/LouisShark/chatgpt_system_prompt.git
  8. Jailbreaks

    Prompts

    A repo for all the jailbreaks

    Stale GitHub, tuxsharxsec 73 ★Updated 4 months ago

    git clone https://github.com/tuxsharxsec/Jailbreaks.git
  9. AutoHarness

    Agents & frameworks

    AutoHarness: Automated Harness Engineering for AI Agents

    Stale GitHub, aiming-lab 450 ★MITUpdated 7 months ago

    git clone https://github.com/aiming-lab/AutoHarness.git
  10. ADR

    MCP servers

    ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

    Stale GitHub, uber 2,090 ★Apache-2.0Updated 16 days ago

    git clone https://github.com/uber/ADR.git
  11. hol-guard

    Agents & frameworks

    Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

    Indexed GitHub, hashgraph-online 1,109 ★Apache-2.0Updated today

    git clone https://github.com/hashgraph-online/hol-guard.git
  12. rebuff

    Prompts

    LLM Prompt Injection Detector

    Stale Archived GitHub, protectai 1,529 ★Apache-2.0Updated 2 years ago 1 note

    git clone https://github.com/protectai/rebuff.git
  13. Scans RAG content/scraped pages for indirect prompt injection

    Stale Official MCP Registry, io.github.4hmetuyar Updated 45 days ago 1 note

    @guardbee/mcp-prompt-injection-scanner@0.2.2
  14. Scans RAG content/scraped pages for indirect prompt injection

    Stale Official MCP Registry, io.github.GuardBee Updated 15 days ago 1 note

    @guardbee/mcp-prompt-injection-scanner@1.2.0
  15. Pliny_HackAPrompt_Dataset

    Datasets & benchmarks

    Hugging Face dataset by hackaprompt

    Stale Hugging Face Hub, hackaprompt 143 ♥cc-by-4.0Updated 15 months ago 1 note

    hackaprompt/Pliny_HackAPrompt_Dataset
  16. skillguard

    Skills

    Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.

    Stale GitHub, obielin 20 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/obielin/skillguard.git
  17. pipelock

    Agents & frameworks

    Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

    Indexed GitHub, pipelab-org 993 ★Apache-2.0Updated yesterday

    git clone https://github.com/pipelab-org/pipelock.git
  18. LLMVault

    AI repositories

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

    Stale GitHub, CyberSunil 342 ★MITUpdated 27 days ago

    git clone https://github.com/CyberSunil/LLMVault.git
  19. Prompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.

    Stale Official MCP Registry, dev.workers.manhliemcn4euwlu.llmrt-companion Updated 13 days ago 1 note

  20. Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.

    Stale Official MCP Registry, dev.agentdiet Updated 26 days ago 1 note

  21. AI-Infra-Guard

    AI repositories

    A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

    Stale GitHub, Tencent 7,471 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/Tencent/AI-Infra-Guard.git
  22. prismor

    Agents & frameworks

    Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

    Indexed GitHub, PrismorSec 487 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/PrismorSec/prismor.git
  23. langkit

    Prompts

    🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀

    Stale GitHub, whylabs 1,000 ★Apache-2.0Updated 24 months ago

    git clone https://github.com/whylabs/langkit.git
  24. Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.

    Stale Official MCP Registry, dev.agentdiet Updated 26 days ago 1 note

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.