Data / Repositories / AI security
AI security repositories on GitHub: 28 ranked by stars
28 public repositories tagged AI security are on GitHub, with 113,843 stars between them; 24 had a push in the last 30 days. Most are written in Python (14), TypeScript (4), Go (3). The most starred: usestrix/strix (68,539), NVIDIA/SkillSpector (20,177), Tencent/AI-Infra-Guard (6,868).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| usestrix/strix | Open-source AI penetration testing tool to find and fix your app’s vulnerabilities. | Python | 68,539 | 7,595 | Apache-2.0 | Oct 14 | Oct 14 |
| NVIDIA/SkillSpector | Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code… | Python | 20,177 | 1,776 | Apache-2.0 | Oct 14 | Oct 14 |
| Tencent/AI-Infra-Guard | A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation. | Python | 6,868 | 661 | Apache-2.0 | Oct 14 | Oct 14 |
| FlorianBruniaux/claude-code-ultimate-guide | The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines. | Python | 6,154 | 808 | CC-BY-SA-4.0 | Oct 13 | Oct 14 |
| CyberStrikeus/CyberStrike | Open-source AI-powered offensive security harness for automated penetration testing. | TypeScript | 3,148 | 516 | AGPL-3.0 | Oct 14 | Oct 14 |
| stacklok/toolhive | ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers. | Go | 2,283 | 319 | Apache-2.0 | Oct 14 | Oct 14 |
| ai-for-developers/awesome-ai-coding-tools | A curated list of AI-powered coding tools | 2,157 | 864 | MIT | Sep 18 | Oct 14 | |
| uber/ADR | ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. | Python | 2,040 | 219 | Apache-2.0 | Oct 13 | Oct 14 |
| hashgraph-online/hol-guard | Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime. | Python | 892 | 158 | Apache-2.0 | Oct 14 | Oct 14 |
| RiccardoBiosas/awesome-MLSecOps | A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain… | Astro | 477 | 121 | MIT | Oct 12 | Oct 14 |
| zhuyansen/agent-skills-hub | Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync | HTML | 447 | 47 | MIT | Oct 14 | Oct 14 |
| graygnatconsole/mcp-audit-tool | 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 | 306 | 5 | MIT | Sep 26 | Oct 15 |
| makalin/SecureMCP | SecureMCP is a security auditing tool designed to detect vulnerabilities and misconfigurations in applications using the [Model Context Protocol (MCP)]( It proactively identifies… | Go | 140 | 19 | MIT | Jun 7, 2025 | Oct 14 |
| knostic/MCP-Scanner | Advanced Shodan-based scanner for discovering, verifying, and enumerating Model Context Protocol (MCP) servers and AI infrastructure tools over HTTP & SSE. | Python | 57 | 8 | MIT | Oct 11 | Oct 14 |
| systempromptio/awesome-ai-agent-governance | The curated list of tools, standards, and resources for governing AI agents in production: policy enforcement, audit trails, EU AI Act compliance, MCP and Claude Code security. | 52 | 90 | Oct 14 | Oct 14 | ||
| badchars/cve-mcp | 23-tool MCP server for CVE & vulnerability intelligence. NVD, EPSS, CISA KEV, GitHub Advisory, OSV — unified in one server. Risk scoring, bulk triage, exploit search. 2… | TypeScript | 32 | 8 | MIT | Sep 17 | Oct 14 |
| nsasoft/nsauditor-ai | NSAuditor AI — Open-source, AI-powered network security scanner. 27 plugins, CVE matching, MITRE ATT&CK mapping, verified vulnerabilities, continuous monitoring, MCP integration.… | JavaScript | 20 | 6 | MIT | Oct 12 | Oct 14 |
| safe-agentic-world/nomos | Deny-wins policy hook for Claude Code and Codex. Checks every shell, file, and fetch call against rules you keep in Git, holds under --dangerously-skip-permissions, refuses… | Go | 19 | 1 | Apache-2.0 | Sep 27 | Oct 14 |
| poojakira/mcp-agent-security-gateway | Default-deny MCP/JSON-RPC security gateway for agent tool-call authorization, prompt-injection detection, exfiltration controls, and audit telemetry. | Python | 17 | 5 | Oct 14 | Oct 14 | |
| shimo4228/contemplative-agent | A long-running experiment: an AI agent posts on its own with a local LLM (Ollama, one 16 GB Mac) and proposes changes to its harness (the constitution, identity and skills in its… | Python | 7 | 2 | MIT | Oct 14 | Oct 14 |
| abbyshade111/StackVet | Turns plain-language answers into a hardened Node/Express web app, then checks it against OWASP ASVS 5.0, AISVS 1.0 and Secure by Design — and reports honestly on what it could… | Rust | 3 | 0 | MIT | Oct 14 | Oct 14 |
| architsharm/agentfox | AgentFox: open-source control plane for AI agents. Guardrails on model traffic, tool calls bounded by capability grants, and a tamper-evident audit trail mapped to compliance… | Python | 3 | 2 | Apache-2.0 | Oct 14 | Oct 14 |
| vasikmansuri/agentconfig-doctor | MCP security scanner & config linter for AI coding agents. Finds leaked secrets, risky commands, broad permissions and invalid MCP servers in Claude Code, Cursor and VS Code… | TypeScript | 3 | 0 | MIT | Oct 14 | Oct 14 |
| bountyoperator/bounty-operator | Find the hole in your bug bounty report before the triager does. Pre-submission review for bounty reports and smart-contract findings, on your own model key. | JavaScript | 2 | 0 | MIT | Oct 14 | Oct 14 |
| AgentPostmortem/MCP-audit | Security scanner and linter for MCP servers. Audits a live server over stdio or HTTP, or a static manifest. 18 rules, SARIF output for GitHub code scanning, zero-config: npx… | TypeScript | 0 | 11 | MIT | Sep 21 | Oct 14 |
| basitalisandhu/agent-skills-state-2026 | Study of 2,999 public agent skill, plugin and MCP repositories (October 2026): missing security policies, unpinned MCP servers, unrestricted shell in skills, front matter that… | Python | 0 | 0 | MIT | Oct 13 | Oct 14 |
| munimtechnologies/self-hosted-ai-security-checklist | Safe defaults and one-line tests for self-hosted AI: Ollama, Open WebUI, vLLM, LiteLLM, ComfyUI, n8n, Dify, Langflow, Flowise, RAGFlow, AnythingLLM. By MV2 of Munim, Inc., with AI… | Python | 0 | 0 | Oct 14 | Oct 14 | |
| tomelias10/mcp-drift-check | Static MCP package-reference mutability checker: Python CLI and GitHub Action. No discovered server execution. Broader config/baseline tools: Orynval Labs. | Python | 0 | 5 | MIT | Oct 11 | Oct 14 |
By language
- Python 14
- TypeScript 4
- Go 3
Related topics
- MCP 18
- LLM security 12
- Security 10
- Claude Code 10
- Prompt injection 9
- Model Context Protocol 9
- AI agents 9
- Agent security 8
- Security scanner 6
- Supply chain security 6
- MCP security 6
- Cursor 6
Read from GitHub by SpecStream between October 14, 2026 and October 15, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.