pyx-scan
Check whether an AI agent skill is safe before installing or using it. Calls the PYX Scanner API to retrieve trust status, risk score, and safety recommendation. Use when agent needs to verify skill safety, or user says "is this safe", "check skill", "scan skill", "verify tool", "pyx scan".
Why use this skill?
Use pyx-scan to verify the safety and trust score of any OpenClaw AI agent skill before installation. Protect your system from malicious or outdated tools.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/fysoul17/pyx-scanWhat This Skill Does
The pyx-scan skill is an essential security utility for the OpenClaw AI ecosystem. It acts as a gatekeeper, allowing you to proactively verify the integrity and safety of any AI agent skill before it is installed or executed. By leveraging the PYX Scanner API, it evaluates code against known security databases, assesses trust scores, and analyzes potential risks to prevent malicious or outdated code from running on your system. It provides immediate, human-readable safety reports that detail why a skill is classified as safe, outdated, or dangerous.
Installation
You can integrate this security layer into your agent by running the following command in your terminal:
clawhub install openclaw/skills/fysoul17/pyx-scan
Once installed, the skill becomes immediately available as a tool for your AI agents to invoke whenever they encounter an unfamiliar or new skill identifier.
Use Cases
- Pre-Installation Audits: Before running an
installcommand, have the agent scan the target skill to ensure it does not possess malicious capabilities. - Security Compliance: Use it as part of an automated workflow to verify all third-party skills in a workspace.
- Risk Mitigation: If an agent requests access to sensitive local files, use pyx-scan to verify that the tool provided is trusted by the PYX community.
Example Prompts
- "Is this skill safe? Scan anthropic/web-search and tell me what the risk level is."
- "Verify the tool developer/tool-name before I proceed with the installation."
- "Please run a pyx scan on github/repo-name and provide a summary of the permissions it requires."
Tips & Limitations
- Always check the
is_outdatedflag; even if a skill was once safe, recent code changes could introduce vulnerabilities. - If a scan returns a 'CAUTION' verdict, perform a manual code audit before proceeding.
- The tool relies on the live PYX Scanner API; ensure your environment has outbound network access to
scanner.pyxmate.comto receive accurate, up-to-the-minute safety reports. - Note that an 'UNSCANNED' status does not mean a skill is dangerous, only that it has not yet been processed by the database. Exercise standard security practices for unknown code.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-fysoul17-pyx-scan": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api