by PACHAKUTlQ · Agent Tool · ★ 147
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 147 |
| Forks | 20 |
| Language | Shell |
| Category | Agent Tool |
| License | AGPL-3.0 |
| Quality Score | 70/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-25 |
| Created | 2025-06-29 |
| Platforms | claude-code, cli |
| Est. Tokens | ~4k |
[!note] Claude Code now officially supports bun runtime and bwrap-based sandbox. It is recommended to use these native features. ClaudeCage might still work. ClaudeCage English | 简体中文 Run the SOTA AI coding agent in a portable, secure sandbox. Claude Code is a state-of-the-art AI coding assistant. Unfortunately, its CLI is distributed as closed-source and obfuscated javascript.
These tools work well together with ClaudeCage for enhanced workflows:
Looking for a ClaudeCage alternative? If you're comparing ClaudeCage 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.
Safely run OpenCode, Codex, Claude Code with full permissions.
🧑🎨 A collection of agentic skills that works
Leash by StrongDM - take your AI agents for a walk
🎯 The definitive collection of 50+ verified Awesome Claude Skills for Claude Code, Claude.ai, and API. Boost
MCP server for SSH: let Claude Code, Codex and any MCP client run commands, transfer files and manage servers
AgentSkillsHub (agentskillshub.top) — security-graded directory of open-source Claude skills, MCP servers & AI
Explore other popular agent tool 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: