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 AMAP-ML · Codex Skill · ★ 2.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is SkillClaw safe to install? View the security audit →
✨ SkillClaw: Let Skills Evolve Collectively with Agentic Evolver ✨ AI agent skills that evolve from every real interaction — just talk.Across sessions, agents, devices, and users. Experience compounds. Skills keep growing. [ and Figma, allowing Agentic AI to c
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Sca
An Agentic Framework for Reflective PowerPoint Generation
🇨🇳 OpenClaw中文用例大全 | 50个真实场景 | 国内特色 + 海外案例的国内适配 | 自动化办公·内容创作·运维·AI助理·知识管理 | 新手友好
Explore other popular codex skill tools:
SkillClaw is Let Skills Evolve Collectively with Agentic Evolver. It is categorized as a Codex Skill with 2.5k GitHub stars.
SkillClaw is primarily written in Python. It covers topics such as agent, agentic-ai, ai-agent.
You can find installation instructions and usage details in the SkillClaw GitHub repository at github.com/AMAP-ML/SkillClaw. The project has 2.5k stars and 243 forks, indicating an active community.
SkillClaw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to SkillClaw on Agent Skills Hub include MemOS, MetaClaw, cursor-talk-to-figma-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: