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 StackOneHQ · MCP Server · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is defender safe to install? View the security audit →
<img src="https://img.shields.io/badge/model-22MB-047B43
| Stars | 121 |
| Forks | 13 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 72.3509856948637/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-14 |
| Created | 2026-02-13 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~17k |
These tools work well together with defender for enhanced workflows:
Looking for a defender alternative? If you're comparing defender 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.
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testab
IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, revi
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先
A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt i
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Explore other popular mcp server tools:
defender is Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.. It is categorized as a MCP Server with 121 GitHub stars.
defender is primarily written in TypeScript. It covers topics such as ai-security, indirect-prompt-injection, llm-security.
You can find installation instructions and usage details in the defender GitHub repository at github.com/StackOneHQ/defender. The project has 121 stars and 13 forks, indicating an active community.
defender is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to defender on Agent Skills Hub include agent-threat-rules, node9-proxy, agentseal. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: