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 jnMetaCode · MCP Server · ★ 139
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is shellward safe to install? View the security audit →
ShellWard AI Agent Security Middleware — Protect AI agents from prompt injection, data exfiltration, and dangerous command execution. ShellWard acts as an LLM security middleware and AI agent firewall, intercepting tool calls at runtime to enforce agent guardrails before damage is done. 8-layer defense-in-depth, DLP-style data flow control, zero dependencies. Works as standalone SDK or OpenClaw plugin. English | 中文 Demo 7 real-world scenarios: server wipe → reverse shell → prompt injection → DLP audit → data exfiltration chain → credential theft → APT attack chain The Problem Your AI agent has full access to tools — shell, email, HTTP, file system. One prompt injection and it can: ❌ Without ShellWard: Agent reads customer file... Tool output: "John Smith, SSN 123-45-6789, card 4532
| Stars | 139 |
| Forks | 24 |
| Language | TypeScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 72.6261568442478/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-28 |
| Created | 2026-03-12 |
| Platforms | claude-code, mcp, node |
| Est. Tokens | ~17k |
These tools work well together with shellward for enhanced workflows:
Looking for a shellward alternative? If you're comparing shellward 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.
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTT
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Explore other popular mcp server tools:
shellward is 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 · 零依赖 · 开源. It is categorized as a MCP Server with 139 GitHub stars.
shellward is primarily written in TypeScript. It covers topics such as agent-security, ai-agent, ai-firewall.
You can find installation instructions and usage details in the shellward GitHub repository at github.com/jnMetaCode/shellward. The project has 139 stars and 24 forks, indicating an active community.
shellward is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to shellward on Agent Skills Hub include node9-proxy, agent-security-scanner-mcp, 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: