AI agent tools for LLM security
Short answer: Our top pick for LLM security: SkillSpector, with the highest AgentPick Score (83/100) among tools tagged "llm-security". Runners-up: nono (78) and toolhive (76). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | SkillSpector | Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chai… | 83/100 | ★ 20k | Apache-2.0 | 14 Oct 2026 |
| #2 | nono | agent runtime security - zero trust, zero setup, zero latency agent sandbox | 78/100 | ★ 4.5k | Apache-2.0 | 14 Oct 2026 |
| #3 | toolhive | ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers. | 76/100 | ★ 2.3k | Apache-2.0 | 14 Oct 2026 |
| #4 | AiSOC | Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agen… | 73/100 | ★ 2.4k | MIT | 14 Oct 2026 |
| #5 | hol-guard | Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runti… | 71/100 | ★ 896 | Apache-2.0 | 14 Oct 2026 |
| #6 | Agentic-Bug-Hunter | AI-powered bug bounty hunting toolkit that works with or without subscription. | 70/100 | ★ 5.3k | MIT | 9 Oct 2026 |
| #7 | ship-safe | The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic co… | 69/100 | ★ 859 | MIT | 9 Oct 2026 |
| #8 | h5i | An agent-native web security workspace. Find vulnerabilities through red-teaming. Formally verify properties of Rust codes in Lean 4. | 69/100 | ★ 777 | Apache-2.0 | 14 Oct 2026 |
| #9 | xalgorix | Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript. | 68/100 | ★ 1.2k | Apache-2.0 | 12 Oct 2026 |
| #10 | pipelock | Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prom… | 68/100 | ★ 929 | Apache-2.0 | 14 Oct 2026 |
| #11 | stride-gpt | An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodolog… | 67/100 | ★ 1.1k | MIT | 13 Oct 2026 |
| #12 | pentest-ai | Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a proof capsule you can replay yourself. | 66/100 | ★ 1.7k | MIT | 9 Oct 2026 |
| #13 | NeuroSploit | NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations… | 66/100 | ★ 1.4k | MIT | 14 Oct 2026 |
| #14 | arcjet-js | Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limit… | 66/100 | ★ 692 | Apache-2.0 | 14 Oct 2026 |
| #15 | open-kritt | Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code. | 63/100 | ★ 2.3k | AGPL-3.0 | 12 Oct 2026 |
| #16 | Dark-Moon | Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM … | 62/100 | ★ 1k | GPL-3.0 | 1 Oct 2026 |
| #17 | api-relay-audit | Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakag… | 62/100 | ★ 881 | AGPL-3.0 | 14 Oct 2026 |
| #18 | vestige | Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorde… | 61/100 | ★ 650 | AGPL-3.0 | 11 Oct 2026 |
| #19 | Cybermes | Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orc… | 60/100 | ★ 940 | Apache-2.0 | 2 Oct 2026 |
| #20 | Claude-BugHunter | A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 … | 59/100 | ★ 5.1k | MIT | 14 Oct 2026 |
| #21 | ADR | ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. | 59/100 | ★ 2k | Apache-2.0 | 14 Oct 2026 |
| #22 | skills | Pashov Audit Group Skills | 59/100 | ★ 1.3k | MIT | 5 Oct 2026 |
| #23 | AutoCVE | Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation. | 58/100 | ★ 1.2k | AGPL-3.0 | 1 Oct 2026 |
| #24 | pentest-ai-agents | Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyz… | 55/100 | ★ 2.3k | MIT | 6 Oct 2026 |
| #25 | pentestcode | PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations. | 54/100 | ★ 845 | MIT | 2 Oct 2026 |
| #26 | agentic_security | Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪 | 52/100 | ★ 2k | Apache-2.0 | 22 Sept 2026 |
| #27 | ai-security-tool | 🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI age… | 52/100 | ★ 622 | MIT | 13 Oct 2026 |
| #28 | medusa | AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions & skills before you clone — plus an alwa… | 48/100 | ★ 1k | AGPL-3.0 | 10 Aug 2026 |
| #29 | numasec | The AI Agent for Cyber Security. | 39/100 | ★ 810 | AGPL-3.0 | 8 May 2026 |
| #30 | agentic-radar | A security scanner for your LLM agentic workflows | 29/100 | ★ 1.1k | Apache-2.0 | 27 Nov 2025 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.