A dedicated security scanner that audits GitHub repositories for vulnerabilities before integrating them into your AI agent environment.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install moltcheck
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 moltcheck 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 moltcheck?
MoltCheck is a specialized security layer designed for the AI agent ecosystem. It provides an automated way to verify the safety of Openclaw Skills by analyzing GitHub repositories for malicious code, credential theft, or unauthorized network activity. By integrating this tool, developers can prevent supply chain attacks and ensure that the skills their agents rely on are trustworthy and safe for production environments.
The tool bridges the gap between raw code and security compliance by providing actionable trust scores and plain-language risk assessments. Whether you are a solo developer or an enterprise, MoltCheck offers the peace of mind required when extending agent capabilities via third-party repositories.
moltcheck Use Cases
- Scanning external Openclaw Skills repositories before local installation.
- Auditing agent permissions to ensure code matches declared SKILL.md specifications.
- Preventing supply chain attacks by detecting hidden network calls or credential harvesting.
- Verifying the safety of open-source AI agent tools during the research and development phase.
How moltcheck Works
- The user provides a GitHub repository URL to the moltcheck skill.
- The skill connects to the MoltCheck API to perform a deep static and behavioral analysis of the repository.
- The system compares the code's actual behavior against the declared permissions in the SKILL.md file.
- A comprehensive report is generated, featuring a trust score (0-100) and a letter grade (A-F).
- The user reviews the plain-language security findings to decide whether to proceed with the installation.
moltcheck Setup
To get started with moltcheck for your Openclaw Skills, follow these steps:
- Initialize the setup to receive your API key and payment instructions:
# Trigger the setup command within your agent
setup
- Configure your API key in the skill configuration file:
{
"apiKey": "mc_your_api_key_here"
}
Note: You can use the free tier which allows for 3 scans per day without an API key.
moltcheck Data Schema & Taxonomy
MoltCheck organizes its output based on security risk levels and permission sets. The following table describes the data returned from a repository scan:
| Property | Description |
|---|---|
| Trust Score | A numeric value (0-100) representing the overall safety level. |
| Grade | A letter grade (A-F) for quick visual assessment. |
| Risks Found | A detailed list of detected vulnerabilities or suspicious code patterns. |
| Permission Analysis | A delta report showing discrepancies between declared and actual code permissions. |
moltcheck Advanced Features
- Automated Permission Auditing: Automatically flags if a skill requests fewer permissions than it actually uses in the source code.
- Bulk Discount Tiers: Scalable pricing for high-volume users needing deep security integration for Openclaw Skills.
- Trust Grading System: Standardized security scoring to help teams set minimum security thresholds for agent skills.
- Plain-Language Risk Communication: Translates complex security vulnerabilities into understandable insights for non-security experts.
SKILL.md
Loading
Related Openclaw Skills
MoltCaptcha
A specialized verification system that uses semantic and mathematical hybrid locks to distinguish AI agents from human users.
Session Memory
A three-layer persistent memory system that converts session transcripts into searchable Markdown and structured glossaries to prevent AI knowledge loss.
spf-write-plan
A precision planning skill that generates structured, test-driven implementation guides for multi-step development tasks.
Superpower with Files
A unified AI workflow combining persistent memory loops with high-speed TDD execution to streamline coding projects.
Clawbridge: AI Connection Scout
Clawbridge is an intelligent scouting agent that transforms your project intent into a nightly automated operation to find and rank professional matches.
Claw-Clawbridge
A high-signal scouting agent that runs nightly to bridge you with the right partners, clients, and collaborators.
METADATA
Featured*
