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 thrashr888 · Codex Skill · ★ 58
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agentkernel safe to install? View the security audit →
agentkernel Run AI coding agents in secure, isolated microVMs. Sub-125ms boot times, real hardware isolation. Installation Quick Start The Command The fastest way to execute code in isolation. Creates a temporary sandbox, runs your command, and cleans up automatically. bash Auto-detects the right runtime from your command agentkernel run python3 script.py # Uses python:3.12-alpine agentke
| Stars | 58 |
| Forks | 5 |
| Language | Rust |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 68.2776091298672/100 |
| Last Updated | 2026-08-24 |
| Created | 2026-01-19 |
| Platforms | claude-code, cli, codex, gemini, rust |
| Est. Tokens | ~27k |
These tools work well together with agentkernel for enhanced workflows:
Looking for a agentkernel alternative? If you're comparing agentkernel 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.
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
A collection of AI agent skills for Clawdbot, Claude Code, Codex
[DEPRECATED] Superseded by systempromptio/systemprompt-template and systempromptio/systemprompt-core. MCP serv
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collabor
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created
Universal development automation for ANY project. Claude Code implements features, runs tests, creates PRs aut
Explore other popular codex skill tools:
agentkernel is Run AI coding agents in secure, isolated microVMs. Sub-125ms boot times, real hardware isolation.. It is categorized as a Codex Skill with 58 GitHub stars.
agentkernel is primarily written in Rust. It covers topics such as agent, ai, claude-code.
You can find installation instructions and usage details in the agentkernel GitHub repository at github.com/thrashr888/agentkernel. The project has 58 stars and 5 forks, indicating an active community.
agentkernel is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agentkernel on Agent Skills Hub include deepcontext-mcp, agent-skills, systemprompt-code-orchestrator. 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: