numasec — security grade SAFE, quality 61/100

Security audit verdict: SAFE · quality 61/100

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 FrancescoStabile · MCP Server · ★ 466

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

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

About numasec

numasec The open source AI security agent. Give your terminal a security brain. Run security workflows with your local tools, agents, runbooks, findings, evidence, replay and reports. npm install -g numasec <img src="https://img.shields.io/github/stars/FrancescoStabile/numasec.svg?style=for-the-badge&label=stars&logo=github&logoColor=white&labelColor=0b0f0a&color=f5a524&cacheSeconds=1800" alt="Gi

ai-agentai-securityappsecbug-bountyclicybersecuritydastdevsecopsethical-hackingllm

Quick Facts

Stars466
Forks51
LanguageTypeScript
CategoryMCP Server
LicenseAGPL-3.0
Quality Score61.1954907678988/100
Open Issues4
Last Updated2026-05-08
Created2026-02-02
Platformsbrowser, cli, mcp, node
Est. Tokens~17967k

Compatible Skills

These tools work well together with numasec for enhanced workflows:

  • pentest-ai-agents — semantic(0.56)+complementary+rare_topics+same_lang+similar_pop+shared_platform (85%)
  • RedteamAgent — semantic(0.54)+complementary+rare_topics+similar_pop+shared_platform (69%)
  • BugTrace-AI — semantic(0.28)+complementary+rare_topics+same_lang+similar_pop+shared_platform (64%)
  • CyberStrike — semantic(0.53)+rare_topics+same_lang+similar_pop+shared_platform (63%)

numasec alternative? Top 6 similar tools

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

  • CyberStrike by CyberStrikeus · ⭐ 1.9k

    Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models,

  • pentest-ai by 0xSteph · ⭐ 1.7k

    Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a

  • pentest-ai-agents by 0xSteph · ⭐ 2.1k

    Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized pene

  • agent-opfor by KeyValueSoftwareSystems · ⭐ 572

    Open-source adversary emulation for AI agents and MCP servers.

  • agentseal by AgentSeal · ⭐ 156

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

  • RedteamAgent by NeoTheCapt · ⭐ 112

    An AI red-team agent for authorized labs and web app pentesting workflows. Turns Claude Code / OpenCode / Code

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is numasec?

numasec is The AI Agent for Cyber Security.. It is categorized as a MCP Server with 466 GitHub stars.

What programming language is numasec written in?

numasec is primarily written in TypeScript. It covers topics such as ai-agent, ai-security, appsec.

How do I install or use numasec?

You can find installation instructions and usage details in the numasec GitHub repository at github.com/FrancescoStabile/numasec. The project has 466 stars and 51 forks, indicating an active community.

What license does numasec use?

numasec is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to numasec?

The top alternatives to numasec on Agent Skills Hub include CyberStrike, pentest-ai, pentest-ai-agents. 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 MCP Server tools