by openguardrails · Codex Skill · ★ 338
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
| Stars | 338 |
| Forks | 49 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 72/100 |
| Last Updated | 2026-04-18 |
| Created | 2025-10-22 |
| Platforms | node |
| Est. Tokens | ~680k |
OpenGuardrails-OSS Protect every action your agent takes. OpenGuardrails is an agent-security platform. OpenGuardrails-OSS is its open-source part — a toolkit for giving an AI agent a health-check and an exam. You drive the work through an agent (OpenClaw, Hermes — any autonomous agent) by asking it in natural language; it then uses OpenGuardrails-OSS to audit itself or other agents.
These tools work well together with openguardrails-oss for enhanced workflows:
Looking for a openguardrails-oss alternative? If you're comparing openguardrails-oss 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.
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, maliciou
Universal adapter between AI agents and model providers
Universal adapter between AI agents and model providers
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (
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:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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: