by joone · Agent Tool · ★ 261
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/joone/loz.gitTaken from the project's README on GitHub. Check the security audit before running it.
Flagged: sudo usage. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
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 | 261 |
| Forks | 15 |
| Language | TypeScript |
| Category | Agent Tool |
| Quality Score | 74/100 |
| Open Issues | 2 |
| Last Updated | 2026-02-17 |
| Created | 2023-02-27 |
| Platforms | cli, node |
| Est. Tokens | ~102k |
What's New v0.4.1 - 2026-02-16 Added Guardrails for dangerous commands: Loz now includes built-in safety guardrails that automatically block potentially dangerous shell commands before execution. The following commands are blocked: and its bypass variants (, ) and commands Fork bomb: Filesystem formatting: Direct disk operations: This feature provides an additional layer of protection to prevent...
Looking for a loz alternative? If you're comparing loz 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.
Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server
Never give AI companies your secrets! A local LLM-based privacy filter for LLM users. Seamless integration wit
🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace
Production-grade GitLab MCP server with 86 tools — full GitLab control from any AI agent (Claude, Cursor, Zed)
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
Your personal AI assistant, running on your own computer. Long-running tasks, real memory, proactive help, voi
Explore other popular agent tool 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: