Armorer — security grade SAFE, quality 63/100

Security audit verdict: SAFE · quality 63/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ArmorerLabs · Codex Skill · ★ 60

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Armorer safe to install? View the security audit →

About Armorer

Armorer Local control plane for AI agents Run OpenClaw, NanoClaw, and future agents with local sandboxes, guided setup, credential handling, guardrails, approvals, jobs, logs, and runtime health in one place. Run any agent. Securely. Local-first by default. Experimental release candidate: Armorer is under active development. The current release train is intended for early testers who are comfortable with local agent runtimes, Docker/Colima, and rapidly evolving setup flows. Website · Install · Docs for humans · [Issues](https://github.com/Armor

agent-runtimeagent-securityai-agentsai-securitycybersecuritydevtoolsdockerguardrailsllm-securitylocal-first

Quick Facts

Stars60
Forks3
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score63.2631773617152/100
Open Issues2
Last Updated2026-08-01
Created2026-02-06
Platformsdocker, node
Est. Tokens~15k

Compatible Skills

These tools work well together with Armorer for enhanced workflows:

  • platform — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
  • shellward — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)

Armorer alternative? Top 6 similar tools

Looking for a Armorer alternative? If you're comparing Armorer with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • ClawGuard by Gk0Wk · ⭐ 99

    The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in co

  • agent-security-scanner-mcp by sinewaveai · ⭐ 121

    Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (

  • rampart by peg · ⭐ 83

    Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,

  • agentseal by AgentSeal · ⭐ 156

    Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha

  • runtm by runtm-ai · ⭐ 296

    Open-source sandboxes where coding agents build and deploy. Spin up isolated environments where Claude Code, C

  • platform by agynio · ⭐ 232

    Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is Armorer?

Armorer is Local control plane for running AI agents with sandboxes, approvals, guardrails, credentials, and runtime health.. It is categorized as a Codex Skill with 60 GitHub stars.

What programming language is Armorer written in?

Armorer is primarily written in TypeScript. It covers topics such as agent-runtime, agent-security, ai-agents.

How do I install or use Armorer?

You can find installation instructions and usage details in the Armorer GitHub repository at github.com/ArmorerLabs/Armorer. The project has 60 stars and 3 forks, indicating an active community.

What license does Armorer use?

Armorer is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to Armorer?

The top alternatives to Armorer on Agent Skills Hub include ClawGuard, agent-security-scanner-mcp, rampart. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools