Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Anthropic-Cybersecurity-Skills
Agents & frameworks817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
git clone https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git -
mcp-observatory
MCP serversMCP security scanner. CI-native testing, attack simulation, health scoring, and SARIF.
@kryptosai/mcp-observatory@1.36.1 -
AiSOC
MCP serversOpen-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
git clone https://github.com/beenuar/AiSOC.git -
JailbreakHub
PromptsA Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
git clone https://github.com/lalipa2003-arch/JailbreakHub.git -
offensive-claude
SkillsOffensive security toolkit for Claude Code covering red team, exploit dev, AD attacks, EDR bypass, mobile pentest
git clone https://github.com/hypnguyen1209/offensive-claude.git -
GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset
Datasets & benchmarksHugging Face dataset by Manusagents
Manusagents/GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset -
zettelforge
MCP serversAgentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
git clone https://github.com/ThreatRecall/zettelforge.git -
FullHunt
Public APIsSearchable attack surface database of the entire internet
-
Claude-Red
Skillsclaude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
git clone https://github.com/SnailSploit/Claude-Red.git -
BloodHound-MCP-AI
MCP serversBloodHound-MCP-AI is integration that connects BloodHound with AI through Model Context Protocol, allowing security professionals to analyze Active Directory attack paths using natural language instead of complex Cypher queries.
git clone https://github.com/MorDavid/BloodHound-MCP-AI.git -
polarity-agent
PromptsPolarity.ai: The AI that refuses to be neutral. It either defends your worst ideas or attacks your objective truths.
git clone https://github.com/HeroBlast10/polarity-agent.git -
Claude-BugHunter
SkillsA Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.
git clone https://github.com/elementalsouls/Claude-BugHunter.git -
Scry
MCP serversFree IPv4 lookups against a distributed attacker-observation corpus.
-
ZeroDOM
MCP serversThe deterministic attack-surface perception layer for AI security agents
zerodom@0.1.5 -
Spyse
Public APIsAccess data on all Internet assets and build powerful attack surface management applications
-
Neetix Liveliness
Public APIsFace liveness, presentation-attack detection and 1:1 face match for identity verification
-
ASMHunter
MCP serversDrive ASMHunter attack-surface monitoring from an AI agent: recon, scans, findings, reports.
asmhunter-mcp@0.1.2 -
BriefBash
MCP serversAI-citation (GEO) teardowns of any website: score, blockers, attack points.
-
arc-security
MCP serversScan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.
arc-security-mcp@0.5.1 -
BlackDome Threat Intel
MCP serversLive honeypot threat intel: attacker IPs, IOCs, credentials, payloads, actors.
blackdome-mcp@0.2.0 -
mcp-watchdog
MCP serversMCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.
mcp-watchdog@0.1.9 -
agentshield-mcp
MCP serversDetect prompt injection, jailbreak, and social-engineering attacks in LLM agents.
@eigenart/agentshield-mcp@0.1.3 -
cloud-audit
MCP serversAWS security scanner with attack chain detection, IAM privilege escalation, and fixes
cloud-audit@2.0.1 -
Cloudflare Radar
MCP serversCloudflare Radar MCP — internet observatory (traffic, attacks, BGP, quality)
@pipeworx/mcp-cloudflare-radar@0.2.1
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.