agent-safehouse — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 eugene1g · Agent Tool · ★ 2.1k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is agent-safehouse safe to install? View the security audit →

About agent-safehouse

Agent Safehouse Sandbox your LLM coding agents on macOS so they can only access the files and integrations they actually need. Agent Safehouse uses with composable policy profiles and a deny-first model. It supports major coding agents and app-hosted agent workflows while keeping normal development usage practical. Philosophy Agent Safehouse is designed around practical least privilege: Start from deny-all. Allow only what the agent needs to do useful work. Keep developer workflows productive. Make risk reduction easy by default. It is a hardening layer, not a perfect security boundary against a determined attacker. Documentation Website: agent-safehouse.dev Docs: agent-safehouse.dev/docs Policy Builder: agent-safehouse.dev/policy-builder Machine-Specific Defaults If you keep shared repos, caches, or team folders in machine-specif

ai-agentsclaude-codellmmacossandboxsecurity

Quick Facts

Stars2,077
Forks95
LanguageShell
CategoryAgent Tool
LicenseApache-2.0
Quality Score64.7427036160694/100
Open Issues24
Last Updated2026-09-22
Created2026-02-09
Platformsclaude-code, cli
Est. Tokens~11k

agent-safehouse alternative? Top 6 similar tools

Looking for a agent-safehouse alternative? If you're comparing agent-safehouse 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.

  • cursor-talk-to-figma-mcp by grab · ⭐ 7.0k

    TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c

  • vllm-mlx by waybarrios · ⭐ 1.6k

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou

  • claude-forge by sangrokjung · ⭐ 822

    oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an ad

  • code-on-incus by mensfeld · ⭐ 728

    Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t

  • vestige by samvallad33 · ⭐ 628

    Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac

  • leash by strongdm · ⭐ 592

    Leash by StrongDM - take your AI agents for a walk

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Shell Agent Tools

Frequently Asked Questions

What is agent-safehouse?

agent-safehouse is Sandbox your local AI agents so they can read/write only what they need. It is categorized as a Agent Tool with 2.1k GitHub stars.

What programming language is agent-safehouse written in?

agent-safehouse is primarily written in Shell. It covers topics such as ai-agents, claude-code, llm.

How do I install or use agent-safehouse?

You can find installation instructions and usage details in the agent-safehouse GitHub repository at github.com/eugene1g/agent-safehouse. The project has 2.1k stars and 95 forks, indicating an active community.

What license does agent-safehouse use?

agent-safehouse is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to agent-safehouse?

The top alternatives to agent-safehouse on Agent Skills Hub include cursor-talk-to-figma-mcp, vllm-mlx, claude-forge. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Agent Tool tools