InnerVault

Library

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

Results

  1. dsh-purge

    Prompts

    基于上游 1.1.71 维护的 dsh-purge 社区兼容包:只负责 DeepSeek Harness 的版本与本地 Windows 运行问题兼容。

    Indexed GitHub, 555bbbAAA 68 ★MITUpdated 6 days ago

    git clone https://github.com/555bbbAAA/dsh-purge.git
  2. wildjailbreak

    Datasets & benchmarks

    Hugging Face dataset by allenai

    Stale Hugging Face Hub, allenai 162 ♥odc-byUpdated 2 years ago 1 note

    allenai/wildjailbreak
  3. 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

  4. agent-opfor

    MCP servers

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

    Stale GitHub, KeyValueSoftwareSystems 583 ★Custom licence (see repository)Updated 33 days ago

    git clone https://github.com/KeyValueSoftwareSystems/agent-opfor.git
  5. This is The most comprehensive prompt hacking course available, which record our progress on a prompt engineering and prompt hacking course.

    Stale GitHub, TrustAI-laboratory 393 ★MITUpdated 19 months ago

    git clone https://github.com/TrustAI-laboratory/Learn-Prompt-Hacking.git
  6. AI Security Research Radar — AI for security and security for AI

    Indexed GitHub, Neetx 8 ★Updated today

    git clone https://github.com/Neetx/ai-security-research-radar.git
  7. dsh-inject

    Prompts

    Advanced model-context injection and request-only rewriting for DeepSeek Harness with native Keysmith rules compatibility.

    Indexed GitHub, john-walks-slow 75 ★MITUpdated 3 days ago

    git clone https://github.com/john-walks-slow/dsh-inject.git
  8. poki

    MCP servers

    Let AI agents operate a real iPhone. Local MCP server and agent, no jailbreak, no extra hardware.

    Indexed GitHub, JosssphZhou 1,381 ★AGPL-3.0Updated today

    git clone https://github.com/JosssphZhou/poki.git
  9. Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.

    Indexed GitHub, langgptai 288 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/langgptai/Awesome-Multimodal-Prompts.git
  10. autoguardrails

    Datasets & benchmarks

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

    Stale GitHub, SantanderAI 129 ★Apache-2.0Updated 46 days ago

    git clone https://github.com/SantanderAI/autoguardrails.git
  11. Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc

    Stale GitHub, motan1337 16 ★MITUpdated 19 days ago

    git clone https://github.com/motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex.git
  12. Gemini Prompts, Gemini 3 Prompts, jailbreak, LLM Prompts, LangGPT —— by 云中江树

    Indexed GitHub, langgptai 499 ★CC0-1.0Updated 2 days ago

    git clone https://github.com/langgptai/awesome-gemini-prompts.git
  13. uptrain

    Prompts

    UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.

    Stale GitHub, uptrain-ai 2,366 ★Apache-2.0Updated 2 years ago

    git clone https://github.com/uptrain-ai/uptrain.git
  14. dataset

    Prompts

    Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

    Stale GitHub, cysecbench 50 ★MITUpdated 22 months ago

    git clone https://github.com/cysecbench/dataset.git
  15. The official website of the Open Trustworthy AI Community (OpenTAI).

    Indexed GitHub, OpenTAI 12 ★Updated today

    git clone https://github.com/OpenTAI/opentai.github.io.git
  16. Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench

    Stale GitHub, hermes-labs-ai 12 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/hermes-jailbench.git
  17. 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
  18. llm-redteam

    MCP servers

    Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints

    Stale Official MCP Registry, io.github.4hmetuyar Updated 49 days ago 1 note

    @guardbee/mcp-llm-redteam@0.1.1
  19. llm-redteam

    MCP servers

    Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints

    Stale Official MCP Registry, io.github.GuardBee Updated 17 days ago 1 note

    @guardbee/mcp-llm-redteam@0.3.1
  20. AI Firewall MCP

    MCP servers

    Multi-agent LLM security layer detecting prompt injection and jailbreaks.

    Stale Official MCP Registry, io.github.Akhilucky Updated 5 months ago 1 note

    ai-firewall-mcp@1.0.1
  21. promptrejectormcp

    MCP servers

    Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.

    Stale Official MCP Registry, io.github.revsmoke Updated 9 months ago 2 notes

    prompt-rejector@1.0.1
  22. agentshield-mcp

    MCP servers

    Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

    Stale Official MCP Registry, io.github.dl-eigenart Updated 7 months ago 2 notes

    @eigenart/agentshield-mcp@0.1.3
  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. esp32-iphone-agent

    MCP servers

    Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.

    Indexed GitHub, onehumanbeing 5,009 ★MITUpdated today

    git clone https://github.com/onehumanbeing/esp32-iphone-agent.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.