safe-shell安全命令行执行器 - 仅允许读取类和查询类命令，阻断所有危险操作。安装命令：npx clawhub@latest install safe-shell
Install via ClawdBot CLI:
clawdbot install chengyusheng188/safe-shellGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
curl \| sh`, `wget \| bashCalls external URL not in known-safe list
https://github.com/your-repo/safe-shellAI Analysis
The skill definition explicitly promotes a read-only, safe shell philosophy and lists only non-destructive commands. The primary risk is the installation command (`npx clawhub@latest install safe-shell`) which fetches and executes code from an external, unspecified repository, introducing a potential supply-chain attack vector.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
IT teams can safely monitor server health, disk usage, and network status across macOS, Linux, and Windows environments without risking accidental modifications. This is ideal for routine checks, troubleshooting, and compliance audits where read-only access is required.
Developers building AI agents can integrate Safe Shell to allow their AI to query system information, file contents, and network diagnostics safely. This prevents the AI from executing dangerous commands while still providing valuable contextual data from the host system.
Schools and training programs can provide students with a safe shell environment to learn command-line basics, system administration concepts, and network diagnostics without the risk of damaging systems. Instructors can demonstrate commands without fear of accidental deletions or modifications.
Security auditors can use Safe Shell to gather system information, check configurations, and review logs across different platforms while maintaining a zero-modification policy. This ensures audit trails remain intact and systems aren't altered during inspection processes.
Support technicians can safely diagnose customer systems by running read-only commands to check hardware, software versions, and network configurations. This allows for effective troubleshooting while eliminating the risk of accidentally modifying customer systems during remote sessions.
Offer tiered licensing for organizations based on number of users, systems, or deployment scale. Include premium features like centralized logging, custom command whitelists, and priority support. This model targets IT departments and managed service providers.
Integrate Safe Shell as a premium component within AI development platforms, command-line toolkits, or DevOps suites. Charge based on API calls, concurrent users, or as part of bundled enterprise packages for development teams building secure applications.
Create specialized versions for educational institutions with classroom management features, progress tracking, and curriculum integration. Offer site licenses for schools, universities, and corporate training programs that need safe environments for teaching system administration.
💬 Integration Tip
Start by integrating Safe Shell into existing monitoring workflows or AI agent frameworks, focusing on its cross-platform command mapping to replace risky manual shell access with controlled, read-only operations.
Scored Apr 19, 2026
Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.
Manage Feishu (Lark) calendars by listing, searching, checking schedules, syncing events, and marking tasks with automated date extraction.
Process multiple items with progress tracking, checkpointing, and failure recovery.
cad reference tool
Search, install, and create OpenClaw skills using intelligent matching across built-in, local, and GitHub skill repositories.
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions.