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 sleepinginsummer · Agent Tool · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is agent-ssh-cli safe to install? View the security audit →
agent-ssh-cli 基于 CLI 的 SSH 代理工具，按 ssh-mcp-server 的能力映射为 Agent 可调用的远端操作能力。 远程执行 · 文件上传 · 文件下载 · 连接配置 · 命令白名单 · 命令黑名单 · Agent Skill 集成 =18" =8" AI 一键安装 · 手动安装 · 配置 · 卸载和清理 · 许可证 · 友情链接 中文 | English 简介 本项目参考 classfang/ssh-mcp-server 的 SSH 操作能力设计，改写为独立 CLI 形式。感谢原项目提供的思路和能力
| Stars | 84 |
| Forks | 8 |
| Language | Rust |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 64.0176398188764/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-11 |
| Created | 2026-04-28 |
| Platforms | cli, rust |
| Est. Tokens | ~23k |
These tools work well together with agent-ssh-cli for enhanced workflows:
Looking for a agent-ssh-cli alternative? If you're comparing agent-ssh-cli with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Power rename/refactor tool for CLI and agent use
Explore other popular agent tool tools:
agent-ssh-cli is Provide the SSH CLI tool for the agent to use。提供给agent使用的 ssh cli 工具。. It is categorized as a Agent Tool with 84 GitHub stars.
agent-ssh-cli is primarily written in Rust.
You can find installation instructions and usage details in the agent-ssh-cli GitHub repository at github.com/sleepinginsummer/agent-ssh-cli. The project has 84 stars and 8 forks, indicating an active community.
agent-ssh-cli is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to agent-ssh-cli on Agent Skills Hub include tutor-skills, repren. 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: