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 Gk0Wk · Codex Skill · ★ 87
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is ClawGuard safe to install? View the security audit →
ClawGuard The antivirus for OpenClaw. Blocks dangerous actions, scans skills, stops secret leaks, and puts humans back in control. 简体中文 · What it is · What works today · Install demo · Demo scenarios · Current limitations · Docs map What it is is the security control layer for OpenClaw. If you are landing on this repository for the first time, the short version is: ClawGuard is The antivirus for OpenClaw. It is designed to sit between OpenClaw and high-risk actions so users can: require human approval before risky actions continue, inspect an
| Stars | 87 |
| Forks | 2 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 61.9230671346043/100 |
| Open Issues | 5 |
| Last Updated | 2026-03-20 |
| Created | 2026-03-11 |
| Platforms | node |
| Est. Tokens | ~145k |
These tools work well together with ClawGuard for enhanced workflows:
Looking for a ClawGuard alternative? If you're comparing ClawGuard 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.
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testab
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, sup
Runtime security for OpenClaw agents. Scan, fix, monitor.
Explore other popular codex skill tools:
ClawGuard is The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in control, for safety.. It is categorized as a Codex Skill with 87 GitHub stars.
ClawGuard is primarily written in TypeScript. It covers topics such as agent-security, ai-security, audit-logs.
You can find installation instructions and usage details in the ClawGuard GitHub repository at github.com/Gk0Wk/ClawGuard. The project has 87 stars and 2 forks, indicating an active community.
The top alternatives to ClawGuard on Agent Skills Hub include agent-security-scanner-mcp, rampart, agent-threat-rules. 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: