A security enforcement layer that scans and scores every skill before installation to prevent malicious code execution.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skill-trust-guard
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 skill-trust-guard 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 Trust Guard?
Trust Guard is a security-focused wrapper designed to safeguard your local environment when working with Openclaw Skills. It acts as a critical gatekeeper between the user and the installation command, ensuring that no skill is added to your system without first undergoing a rigorous safety check via the trust scanner. By enforcing a scan-first-install-later policy, it significantly reduces the risk of supply chain poisoning and malicious script execution.
This tool is essential for developers and teams who want to maintain a hardened development environment while leveraging the power of Openclaw Skills. It integrates seamlessly into existing workflows by using a PATH shim to override default installation commands, making security an invisible but robust part of your daily operations.
Trust Guard Use Cases
- Preventing the installation of high-risk or unverified Openclaw Skills on local machines.
- Automating security audits within developer environments to identify potential supply chain attacks.
- Hardening your AI agent infrastructure by enforcing a mandatory trust score for all imported logic.
- Standardizing security protocols across a team of developers using Openclaw Skills.
How Trust Guard Works
- The user initiates an installation command for new Openclaw Skills using the provided wrapper or shim.
- Trust Guard invokes the skill-trust-scanner to perform a technical audit of the target skill's source code.
- A safety score is generated based on the scanner's analysis of the skill's dependencies and execution scripts.
- The guard evaluates the score against pre-defined policies: scores below 50 are blocked, scores between 50 and 74 require manual confirmation, and scores 75 or above proceed automatically.
- If the security criteria are met, the tool hands off the process to the standard CLI to complete the installation.
Trust Guard Setup
To secure your Openclaw Skills, run the integration script and update your system path:
# Run the integration script to generate the PATH shim
~/.openclaw/skills/skill-trust-guard/integrate.sh
# Add the secure bin directory to your PATH
export PATH="$HOME/.openclaw/bin:$PATH"
After setup, any standard installation command will be automatically intercepted by Trust Guard.
Trust Guard Data Schema & Taxonomy
Trust Guard evaluates Openclaw Skills using a specific scoring taxonomy to determine installation eligibility:
| Score Range | Status | Action |
|---|---|---|
| < 50 | High Risk | Blocked: Installation is rejected to protect the system. |
| 50 - 74 | Moderate Risk | Warning: Manual confirmation or the --yes flag is required. |
| >= 75 | Trusted | Verified: Installation proceeds without interruption. |
The tool maintains its configuration and shims within the ~/.openclaw/ directory structure.
Trust Guard Advanced Features
- Transparent CLI wrapping through the use of a PATH shim for seamless protection of Openclaw Skills.
- Support for multiple installation sources including local paths, slugs, and remote Git URLs.
- Pre-install hooks that can be customized to include additional organizational safety checks.
- Automatic blocking logic that prevents human error when handling potentially toxic Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Kimi CLI Coding Agent Skill
An advanced AI coding executor that enables agents to generate, refactor, and debug complex multi-file projects using the Kimi Code CLI.
Ralph: AI CLI Automation Loop Generator
Ralph is a specialized command generator that creates robust automation loops for running AI CLI tools like Claude Code and Gemini through local terminal environments.
Crypto Whale Monitor
A specialized blockchain monitoring skill that uses Web3 RPC to track large-scale liquidity movements from whale wallets.
multisage
A powerful multi-model synthesis tool that queries Claude, GPT, and Gemini simultaneously to provide comprehensive, expert-vetted answers.
YouTube Lecture Transcript Analyzer
A powerful CLI tool to transform YouTube video transcripts into structured lecture notes, evidence-backed claims, and actionable checklists.
YouTube Lecture Transcript Analyzer
A professional tool for extracting core structural insights, key arguments, and actionable steps from YouTube lecture transcripts.
Featured*
