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 tomascupr · Agent Tool · ★ 448
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sandstorm safe to install? View the security audit →
Sandstorm Open-source runtime for general-purpose AI agents in isolated sandboxes. CLI, API, Python client, and Slack with streaming, file uploads, and config-driven behavior. Built on the Claude Agent SDK and E2B. Sandstorm is for people who want real agent work, not a chat wrapper: Research Acme's competitors, crawl their sites and recent news, and write a one-page branded briefing PDF with sources Analyze uploaded transcripts or PDFs Triage incoming support tickets Run a security audit in a fresh sandbox Turn docs into a draft API spec Terminal demo The point is not that an agent can answer a
| Stars | 448 |
| Forks | 42 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 67.0083803915472/100 |
| Open Issues | 1 |
| Last Updated | 2026-04-24 |
| Created | 2026-02-14 |
| Platforms | claude-code, cli, python |
| Est. Tokens | ~46k |
These tools work well together with sandstorm for enhanced workflows:
Looking for a sandstorm alternative? If you're comparing sandstorm 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.
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, Git
MaverickMCP - Personal Stock Analysis MCP Server
Your AI agent army, commanded from Slack/Discord/Telegram/Wechat/Lark. Stream Claude Code, OpenCode, or Codex
AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while pr
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic
Full-stack AI app generator — FastAPI + Next.js with agents, RAG, streaming, auth, and 20+ integrations out of
Explore other popular agent tool tools:
sandstorm is Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructure.. It is categorized as a Agent Tool with 448 GitHub stars.
sandstorm is primarily written in Python. It covers topics such as agent-sdk, ai, ai-agents.
You can find installation instructions and usage details in the sandstorm GitHub repository at github.com/tomascupr/sandstorm. The project has 448 stars and 42 forks, indicating an active community.
sandstorm is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to sandstorm on Agent Skills Hub include claudex, maverick-mcp, vibe-remote. 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: