A specialized configuration skill for managing security levels and execution permissions within the OpenClaw environment.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-exec-permission
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 openclaw-exec-permission 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 OpenClaw Exec Permission Configuration?
The OpenClaw Exec Permission skill is a fundamental configuration framework designed to govern how AI agents interact with system-level commands. By leveraging Openclaw Skills, developers can fine-tune the balance between autonomous agent capabilities and system security through the management of the tools.exec parameters.
This skill provides the technical blueprint for defining security tiers—ranging from restricted allowlists to full unrestricted access—and determining the manual approval workflow for command execution. It ensures that Openclaw Skills operate within a predictable and secure boundary tailored to specific environments like production or private development.
OpenClaw Exec Permission Configuration Use Cases
- Restricting AI agents to a specific set of safe commands in production using an allowlist.
- Enabling seamless, unprompted command execution for high-velocity local development.
- Implementing a 'human-in-the-loop' approval process for sensitive system operations.
- Protecting private servers by enforcing strict execution security protocols.
How OpenClaw Exec Permission Configuration Works
- The user identifies the required security posture for their Openclaw Skills implementation.
- Manual modification of the openclaw.json configuration file is performed to define the security and ask parameters.
- The system evaluates the security level (deny, allowlist, or full) to determine if a command is inherently permitted.
- The ask mode (off, always, or on-miss) dictates whether the user is prompted for permission before execution.
- The OpenClaw gateway is restarted to initialize the updated permission schema.
OpenClaw Exec Permission Configuration Setup
To configure Openclaw Skills execution permissions, you must directly edit the configuration file as these are protected paths.
# Example: Setting security to full and turning off manual approval
python3 -c "
import json
with open('/home/zzclaw/.openclaw/openclaw.json') as f:
c = json.load(f)
c['tools']['exec']['security'] = 'full'
c['tools']['exec']['ask'] = 'off'
with open('/home/zzclaw/.openclaw/openclaw.json', 'w') as f:
json.dump(c, f, indent=2, ensure_ascii=False)
print('Configuration Updated')
"
# Restart the gateway to apply changes
openclaw gateway restart
OpenClaw Exec Permission Configuration Data Schema & Taxonomy
The skill utilizes a structured JSON schema within the core configuration to manage permissions for Openclaw Skills:
| Parameter | Value Options | Function |
|---|---|---|
| security | deny, allowlist, full | Defines the overall execution restriction level. |
| ask | off, always, on-miss | Determines the user intervention frequency. |
| allowlist | Array of Strings | Specifies permitted command patterns (e.g., "git *", "npm *"). |
OpenClaw Exec Permission Configuration Advanced Features
- Pattern-based allowlisting to support wildcards in command arguments.
- Protected configuration paths to prevent agents from self-escalating their own permissions.
- Multi-tier environment templates for rapid switching between production-safe and development-loose modes.
- Granular control over the gateway approval lifecycle for Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Aliyun Cloudauth Verify
Automate Alibaba Cloud ID Verification (Cloudauth) resource management and API troubleshooting using OpenAPI and official SDKs.
Task Planner
An intelligent planning engine that decomposes high-level goals into structured, prioritized action items using the Plan-and-Solve pattern.
Presentation Maker
An AI-powered presentation generator that transforms outlines into professional slide decks using Tree of Thoughts organization.
Hot Trends & Demand Mining
An automated tool for scraping and analyzing real-time hot search data across major platforms without needing API keys.
Hotel Price Finder
A high-performance AI agent skill for real-time hotel price comparison across multiple online travel agencies without mandatory API keys.
Aliyun Cloud Firewall Management
A specialized tool for managing Alibaba Cloud Cloud Firewall (Cloudfw) through OpenAPI and SDK integration for automated policy management and troubleshooting.
Featured*
