Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by SleuthCo · Agent Tool · ★ 130
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is clawshield-public safe to install? View the security audit →
ClawShield Security proxy for AI agents. Sits in front of OpenClaw and scans every message for prompt injection, PII leaks, and secrets — before they reach the model or leave the network. Ships with 5 specialized AI agents, a built-in dashboard, and a YAML policy engine. One command to start. Quickstart (Docker) Prerequisites: Docker and an Anthropic API key. Open http://localhost:18801 in your browser. You'll see the ClawShield dashboard with 5 AI agents ready to chat. That's it. ClawShield is scanning all
| Stars | 130 |
| Forks | 18 |
| Language | Go |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 70.1792506685514/100 |
| Open Issues | 10 |
| Last Updated | 2026-03-26 |
| Created | 2026-03-01 |
| Platforms | aws, go |
| Est. Tokens | ~199k |
These tools work well together with clawshield-public for enhanced workflows:
Looking for a clawshield-public alternative? If you're comparing clawshield-public with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
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
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, sup
ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers
AgentWard – Built for all, hardened for OpenClaw.
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
Explore other popular agent tool tools:
clawshield-public is Security proxy for AI agents. Scans every message for prompt injection, PII, and secrets. Defense-in-depth: Go proxy + iptables firewall + eBPF kernel monitor. YAML policy engine, audit logging, 5 AI . It is categorized as a Agent Tool with 130 GitHub stars.
clawshield-public is primarily written in Go. It covers topics such as ai-agents, ai-security, audit-logging.
You can find installation instructions and usage details in the clawshield-public GitHub repository at github.com/SleuthCo/clawshield-public. The project has 130 stars and 18 forks, indicating an active community.
clawshield-public is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to clawshield-public on Agent Skills Hub include shellward, rampart, openclaw-skills-security. 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: