A dedicated security skill that identifies and audits dangerous shell command patterns before execution to prevent system compromise.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install run-command-safety-check
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install run-command-safety-check using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Command Execution Safety Inspector?
The Command Execution Safety Inspector is a critical security layer designed for AI agents to prevent the execution of hazardous shell operations. By leveraging this tool within the Openclaw Skills ecosystem, developers can automatically scan scripts for pipe-to-shell vulnerabilities, recursive deletions, and obfuscated commands that might lead to data loss or security breaches. It acts as an automated auditor, ensuring that every shell-based task follows strict safety protocols.
This skill transforms raw command input into a structured security report, highlighting risks and suggesting safer alternatives. It is an indispensable asset for anyone using AI to automate terminal-based workflows, providing a necessary bridge between AI-generated code and secure system administration. By integrating these Openclaw Skills, you ensure that high-risk actions are flagged for manual review before any damage can occur.
Command Execution Safety Inspector Use Cases
- Detecting dangerous pipe-to-shell patterns in AI-generated scripts.
- Identifying high-risk file operations like rm -rf or overwriting redirections.
- Auditing shell commands for obfuscation or hidden malicious execution.
- Generating secure dry-run reports before executing complex automation tasks.
- Validating command safety in multi-agent collaborative environments.
How Command Execution Safety Inspector Works
- The skill receives shell command text, script files, or directory paths as input for analysis.
- It reorganizes the input into a structured task format to ensure no command parameters are overlooked.
- The engine scans the commands against a predefined security specification to identify high-risk and medium-risk patterns.
- If the context is unclear, the skill generates a list of items pending confirmation rather than assuming intent.
- It produces a comprehensive security report using a standardized template, including risk levels and alternative syntax.
- A final recommendation is provided to guide the user on whether to proceed, modify, or reject the command.
Command Execution Safety Inspector Setup
To utilize this security tool within your Openclaw Skills environment, ensure Python 3 is installed on your system. Follow these configuration steps:
# Navigate to the skill directory
cd run-command-safety-check
# Execute a safety audit on a target script
python3 ./scripts/run.py --input your_script.sh --output safety_report.md
Command Execution Safety Inspector Data Schema & Taxonomy
The Command Execution Safety Inspector organizes data using specific local resources to maintain consistency across audits:
| Resource | Type | Purpose |
|---|---|---|
| spec.json | Configuration | Defines the signatures for dangerous command patterns and security rules. |
| template.md | Markdown | The structural layout for generating consistent security reports. |
| run.py | Script | The core logic engine that performs the command parsing and risk analysis. |
| examples/ | Directory | Provides reference materials for expected safety check outputs. |
Command Execution Safety Inspector Advanced Features
- Dry-run generation to visualize command impact without system modification.
- Automated boundary detection for high-risk environments involving privacy or restricted permissions.
- Support for custom security specifications via the spec.json configuration file.
- Seamless integration as a safety gate for other Openclaw Skills that require terminal access.
- Detailed audit trails that prioritize read-only and roll-back capabilities.
SKILL.md
Loading
Related Openclaw Skills
Personal Deadline Radar
An intelligent scanning tool designed to identify upcoming deadline risks and scheduling conflicts across tasks, meetings, and messages.
Permission Footprint Reviewer
A specialized security auditor that analyzes the permission requirements of scripts and skills to enforce least-privilege principles.
Partner Enablement Kit
Automate the creation of tailored enablement packages for channel partners including FAQs, versioning, and resource lists.
Onboarding Journey Designer
A structured AI tool for designing Day 1, 7, and 30 onboarding milestones for customers and employees.
SBOM Explainer
An AI-powered skill that converts technical SBOM data into prioritized, human-readable risk assessments.
screenshot-to-task
A specialized tool for Openclaw Skills that transforms visual inspirations and screenshot context into structured, prioritized task lists.
METADATA
Featured*
