AI agent tools for agent security
Short answer: Our top pick for agent security: SkillSpector, with the highest AgentPick Score (83/100) among tools tagged "agent-security". Runners-up: nono (78) and agent-beacon (72). 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 | agent-beacon | The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu | 72/100 | ★ 1.8k | MIT | 14 Oct 2026 |
| #4 | 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 |
| #5 | 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 |
| #6 | ANOLISA | ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response com… | 69/100 | ★ 619 | Apache-2.0 | 14 Oct 2026 |
| #7 | 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 |
| #8 | 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 |
| #9 | agent-safe-pipeline | An execution-authority gateway for AI agents and APIs. It intercepts consequential HTTP actions, asks Decionis whether they are authorized, and forwar… | 66/100 | ★ 688 | Apache-2.0 | 13 Oct 2026 |
| #10 | emilia-protocol | Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol k… | 64/100 | ★ 611 | Apache-2.0 | 13 Oct 2026 |
| #11 | Sponsio | Deterministic safety solutions for probabilistic AI agents | 64/100 | ★ 454 | Apache-2.0 | 14 Oct 2026 |
| #12 | guardana | Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release de… | 63/100 | ★ 287 | Apache-2.0 | 14 Oct 2026 |
| #13 | SkillEvaluator | Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live … | 62/100 | ★ 568 | Apache-2.0 | 14 Oct 2026 |
| #14 | 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 |
| #15 | node9-proxy | Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, … | 61/100 | ★ 220 | Apache-2.0 | 14 Oct 2026 |
| #16 | 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 |
| #17 | Adrian | Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real … | 59/100 | ★ 583 | Apache-2.0 | 15 Sept 2026 |
| #18 | numbat | Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction. | 54/100 | ★ 1.1k | Apache-2.0 | 14 Oct 2026 |
| #19 | agentic_security | Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪 | 52/100 | ★ 2k | Apache-2.0 | 22 Sept 2026 |
| #20 | Aegis | Runtime policy enforcement for AI agents. Cryptographic audit trail, human-in-the-loop approvals, kill switch. Zero code changes. | 51/100 | ★ 542 | MIT | 9 Oct 2026 |
| #21 | nasiko | The Open Runtime for AI Agents | 49/100 | ★ 9.5k | See repo | 7 Oct 2026 |
| #22 | 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 |
| #23 | mcp-audit-tool | 🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command inje… | 29/100 | ★ 295 | MIT | 26 Sept 2026 |
| #24 | agentseal | Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resist… | 27/100 | ★ 377 | See repo | 11 Jun 2026 |
| #25 | mcp-gateway | A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents. | 24/100 | ★ 396 | MIT | 22 Jan 2026 |
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.