InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

Looks like a goal we have a starting path for: I want to research potential clients

  1. skills

    Skills

    Trail of Bits skills for security research, vulnerability detection, and audit workflows

    Stale GitHub, trailofbits 7,848 ★CC-BY-SA-4.0Updated 19 days ago

    git clone https://github.com/trailofbits/skills.git
  2. gpt6-Astra

    Prompts

    gpt6 Astra-claude-grok4.7-deepseekv4.1flash-glm5.3-gemini破甲越狱 · 冷咖啡 BREAK//OPEN 工作台

    Indexed GitHub, 3641397194-wq 2,255 ★MITUpdated yesterday

    git clone https://github.com/3641397194-wq/gpt6-Astra.git
  3. skills

    Skills

    Pashov Audit Group Skills

    Stale GitHub, pashov 1,255 ★MITUpdated 42 days ago

    git clone https://github.com/pashov/skills.git
  4. Search CVEs, source software/version evidence, KEV, EPSS and public security research.

    Stale Official MCP Registry, ai.excessionlabs Updated 4 days ago 1 note

  5. 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
  6. binny

    Agents & frameworks

    BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.

    Indexed GitHub, openbin-ai 247 ★AGPL-3.0Updated today

    git clone https://github.com/openbin-ai/binny.git
  7. Read AI security guides and lab research, and request an LLM or AI agent security assessment.

    Stale Official MCP Registry, com.airedteamingservices Updated 6 days ago 1 note

  8. Reusable prompts for a structured, evidence-first bug bounty hunting workflow

    Stale GitHub, mdpsec 604 ★MITUpdated 44 days ago

    git clone https://github.com/mdpsec/bug-bounty-hunting-prompts.git
  9. open-kritt

    Agents & frameworks

    Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

    Stale GitHub, Kritt-ai 2,291 ★AGPL-3.0Updated 35 days ago

    git clone https://github.com/Kritt-ai/open-kritt.git
  10. 0security

    Agents & frameworks

    Sovereign infrastructure to build and deploy security agents that find, prove and fix security risks. Open source. Web UI, CLI, CI and MCP.

    Indexed GitHub, 0sec-labs 1,371 ★Apache-2.0Updated today

    git clone https://github.com/0sec-labs/0security.git
  11. ablation

    AI repositories

    Ablation is an AI-assisted reverse engineering (AIARE) framework

    Stale GitHub, Ablation-Tool 224 ★Custom licence (see repository)Updated 21 days ago

    git clone https://github.com/Ablation-Tool/ablation.git
  12. AIRTBench-Code

    Datasets & benchmarks

    Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models

    Stale GitHub, dreadnode 111 ★Apache-2.0Updated 32 days ago

    git clone https://github.com/dreadnode/AIRTBench-Code.git
  13. 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
  14. 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
  15. update-hijack-poc

    MCP servers

    PoC benign MCP server for update-hijack security research

    Stale Official MCP Registry, io.github.NOTTIBOY137 Updated 9 months ago 1 note

    @nottiboy1337/mcp-update-hijack-poc@1.0.1
  16. open-registry-poc

    MCP servers

    PoC: Open Registry supply chain — unvetted server listing (security research)

    Stale Official MCP Registry, io.github.NOTTIBOY137 Updated 9 months ago 1 note

    @nottiboy1337/mcp-open-registry-poc@1.0.0
  17. Free open-source OSINT and investigation toolkit for Claude Code: case management, 54 OSINT enrichment adapters, structured analytic techniques (ACH), chain-of-custody evidence capture, and threat-intel MCP servers. MIT.

    Stale GitHub, assafkip 54 ★MITUpdated 23 days ago

    git clone https://github.com/assafkip/investigators-copilot.git
  18. harness-for-rea

    MCP servers

    Desktop app and terminal UI for deep analysis of software you own: an orchestrator plans, a sandboxed Claude Code specialist reverse engineers in Docker, with REA and Cheat Engine over MCP.

    Stale GitHub, protonspy 27 ★MITUpdated 5 days ago

    git clone https://github.com/protonspy/harness-for-rea.git
  19. readme-canary

    MCP servers

    Security research canary remote MCP server for owned-account testing.

    Stale Official MCP Registry, io.github.brkd-h1 Updated 3 months ago 1 note

  20. pentest-mcp-server

    MCP servers

    Offline methodology engine for authorized penetration testing, CTF, and security research.

    Stale Official MCP Registry, io.github.cyanheads Updated 17 days ago 2 notes

    @cyanheads/pentest-mcp-server@0.3.0
  21. hyperion

    MCP servers

    Hyperion — MCP tool marketplace for AI agents: web, OSINT, security, research via one key.

    Stale Official MCP Registry, com.thetempleofdoom.hyperion Updated 2 months ago 1 note

  22. pentest-ai-agents

    Agents & frameworks

    Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

    Stale GitHub, 0xSteph 2,330 ★MITUpdated 41 days ago

    git clone https://github.com/0xSteph/pentest-ai-agents.git
  23. Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.

    Stale Official MCP Registry, dev.gtfo Updated 4 months ago 1 note

  24. Temporary authorized security research probe. Safe to ignore. Will be removed shortly.

    Stale Official MCP Registry, io.github.SSJCorpSec Updated 4 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.