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 FIND-Lab · Codex Skill · ★ 63
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AgentWard safe to install? View the security audit →
AgentWard · 玄甲OS AgentWard (玄甲) is a full-stack security operating system purpose-built for trustworthy, scalable AI agent deployment, with native code adaptation to OpenClaw. AgentWard unifies agent onboarding, secure reasoning, and trusted execution in one cohesive security architecture, with upcoming native support for other leading mainstream agent frameworks. Its heterogeneous defense-in-depth design rearchitects the agent workflow into five coordinated security layers across startup, perception, memory, decision-making, and execution, with dynamic cross-stage protections that verify foundation integrity, block adversarial deception, stop memory tampering, and validate every autonomous decision and high-risk command — a complete, end-to-end closed security loop that delivers on the promise of "trustworthy at inception, controllable throughout the process, and reliable in outcomes". If you find this repo useful, please cite our paper on the design of AgentWard architecture: Why AgentWard 🛡️ Comprehensive Risk Coverage — Heterogeneous Defense-in-Depth (DiD) a
| Stars | 63 |
| Forks | 9 |
| Language | TypeScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 64.9019590098854/100 |
| Last Updated | 2026-06-04 |
| Created | 2026-03-20 |
| Platforms | node |
| Est. Tokens | ~167k |
These tools work well together with AgentWard for enhanced workflows:
Looking for a AgentWard alternative? If you're comparing AgentWard 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.
User-friendly orchestrator for OpenClaw
Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Save 120+ Hours of Setup Pain (I did it for you) – Launch Your OpenClaw Agent Teams with 1 Command (15+ Recipe
Security plugin for OpenClaw agents - prevents secret leaks, PII exposure, and destructive command execution
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, sup
Explore other popular codex skill tools:
AgentWard is AgentWard – Built for all, hardened for OpenClaw.. It is categorized as a Codex Skill with 63 GitHub stars.
AgentWard is primarily written in TypeScript. It covers topics such as agent-security, defense-in-depth, llm-agent.
You can find installation instructions and usage details in the AgentWard GitHub repository at github.com/FIND-Lab/AgentWard. The project has 63 stars and 9 forks, indicating an active community.
AgentWard is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to AgentWard on Agent Skills Hub include claworc, clawshield-public, agent-security-scanner-mcp. 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: