llm-shell-guardBlocks destructive Linux commands by enforcing allowlist execution, denylist checks, regex detection, protected paths, and approval for risky actions.
Install via ClawdBot CLI:
clawdbot install jurgenw81/llm-shell-guardGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Accesses sensitive credential files or environment variables
/etc/passwdPotentially destructive shell commands in tool definitions
rm -rf /Calls external URL not in known-safe list
http://example.com/x.shAI Analysis
The skill is a defensive security policy definition for command validation; it contains no executable code, external API calls, or data exfiltration mechanisms. The rule-based signals flagged are examples of patterns the skill is designed to detect and block, not actions the skill itself performs.
Audited Apr 16, 2026 · audit v1.0
Generated Aug 8, 2026
Security teams can use this skill to ensure that only safe commands are executed during automated security audits on Linux systems. It prevents accidental or malicious command execution that could compromise the audit process.
In DevOps pipelines, this skill can be integrated as a gate before executing deployment scripts or system administration commands, ensuring compliance with safety policies and reducing the risk of unauthorized changes.
For AI agents that assist with system administration tasks, this skill enforces a strict allowlist policy, preventing harmful commands from being executed and requiring human approval for high-risk actions.
When managing cloud instances, this skill adds an extra layer of security by blocking dangerous commands like package managers and protected-path writes, safeguarding critical cloud resources.
Offer a cloud-based security platform that integrates with this skill to monitor and enforce command safety for AI agents across multiple client environments, charged via monthly subscription.
Provide consulting services to enterprises implementing this skill as part of their AI agent security strategy, including customization, integration, and training.
Release the skill as open source to gain adoption, then offer premium support, advanced features, and compliance reporting as paid add-ons.
💬 Integration Tip
Integrate this skill as a pre-execution gate for all shell commands in your agent's workflow, and pair it with a sandbox environment for best results.
Scored Aug 8, 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.