by XSafeAI · Codex Skill · ★ 166
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pip install xsafeclaw
pip install git+https://github.com/XSafeAI/XSafeClaw.gitTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 166 |
| Forks | 7 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 64/100 |
| Last Updated | 2026-07-10 |
| Created | 2026-03-10 |
| Platforms | python |
| Est. Tokens | ~17k |
English · 中文文档 XSafeClaw: Monitor and Secure Your Agents 🚀 🔥🔥 Now supporting OpenClaw, Hermes, and Nanobot! 🔥🔥 AI agents are not just new software. They are software that can be talked into doing dangerous things.
Looking for a XSafeClaw alternative? If you're comparing XSafeClaw 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.
Deterministic safety solutions for probabilistic AI agents
A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt i
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, sup
Think before doing, prove before saving. Vestige is the local-first cognitive operating system and determinist
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha
🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for se
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: