Urlscan logo

Urlscan

Organization
taracodlabs
urlscan

Submit URLs to urlscan.io — safety verdict + screenshot retrieval

Overview

Publishertaracodlabs
Repositoryaiden
Skill nameurlscan
Stars
852
Forks
150
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by taracodlabs on GitHub. Read the source before you install it.

Installation

Install the Urlscan AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/taracodlabs/aiden/tree/main/skills/urlscan
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/taracodlabs/aiden.git /tmp/aiden
mkdir -p .claude/skills
cp -r /tmp/aiden/skills/urlscan .claude/skills/urlscan
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Urlscan in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Urlscan on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Urlscan is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

URL Safety Scanner (urlscan.io)

Submit any URL for analysis and receive a safety verdict, screenshot, and DNS/HTTP metadata. Uses the urlscan.io API.

Requires: Free URLSCAN_API_KEY — sign up at urlscan.io, no credit card needed.

When to Use

  • User receives a suspicious link and wants to check it safely
  • User wants to verify if a URL is phishing or malware
  • User asks "is this link safe?" or "scan this URL for threats"
  • Security review of links before sharing them
  • OSINT: see what a URL looks like without visiting it yourself

How to Use

Submit a URL for scanning

powershell
$url    = "https://suspicious-site.example.com"
$key    = $env:URLSCAN_API_KEY
$body   = '{"url": "' + $url + '", "visibility": "unlisted"}'

$submit = Invoke-RestMethod -Uri "https://urlscan.io/api/v1/scan/" `
    -Method POST `
    -Headers @{ "API-Key" = $key; "Content-Type" = "application/json" } `
    -Body $body

Write-Host "Scan submitted!"
Write-Host "UUID:    $($submit.uuid)"
Write-Host "Results: $($submit.result)"
Write-Host "Waiting 30 seconds for scan to complete..."
Start-Sleep -Seconds 30

Retrieve scan results after waiting

powershell
$uuid   = "PASTE-UUID-FROM-SUBMIT-STEP"
$key    = $env:URLSCAN_API_KEY

$result = Invoke-RestMethod -Uri "https://urlscan.io/api/v1/result/$uuid/" `
    -Headers @{ "API-Key" = $key }

Write-Host "Final URL:   $($result.page.url)"
Write-Host "IP:          $($result.page.ip)"
Write-Host "Country:     $($result.page.country)"
Write-Host "Malicious:   $($result.verdicts.overall.malicious)"
Write-Host "Phishing:    $($result.verdicts.overall.phishing)"
Write-Host "Score:       $($result.verdicts.overall.score)"
Write-Host "Screenshot:  https://urlscan.io/screenshots/$uuid.png"

One-shot: submit and wait for result

powershell
function Scan-Url {
    param([string]$TargetUrl, [string]$ApiKey = $env:URLSCAN_API_KEY)

    $body   = '{"url": "' + $TargetUrl + '", "visibility": "unlisted"}'
    $submit = Invoke-RestMethod -Uri "https://urlscan.io/api/v1/scan/" `
        -Method POST -Headers @{ "API-Key" = $ApiKey; "Content-Type" = "application/json" } `
        -Body $body
    $uuid = $submit.uuid

    Write-Host "Scanning $TargetUrl (uuid: $uuid)..."
    Start-Sleep -Seconds 30

    $result = Invoke-RestMethod -Uri "https://urlscan.io/api/v1/result/$uuid/" `
        -Headers @{ "API-Key" = $ApiKey }

    [PSCustomObject]@{
        URL       = $result.page.url
        IP        = $result.page.ip
        Malicious = $result.verdicts.overall.malicious
        Phishing  = $result.verdicts.overall.phishing
        Score     = $result.verdicts.overall.score
        Report    = "https://urlscan.io/result/$uuid/"
    }
}

Scan-Url -TargetUrl "https://example.com"

Examples

"Check if this link is safe: https://bit.ly/abc123" → Submit with visibility "unlisted", wait 30 seconds, retrieve result.

"Scan this suspicious email link for phishing" → Use the one-shot function above. If Phishing = True, warn the user.

"I want to see what this URL looks like without clicking it" → Submit the scan, then use the screenshot URL: https://urlscan.io/screenshots/{uuid}.png

Cautions

  • Scans take 20–60 seconds to complete — always wait before fetching results
  • "visibility": "public" makes the scan visible to all urlscan.io users — use "unlisted" for sensitive URLs
  • Do not scan URLs that contain personal data or credentials in query parameters
  • Free tier allows ~5 scans per minute — add delays for bulk scanning
  • The API key is required to submit scans; public search results are accessible without a key

Requirements

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Urlscan AI skill do?

Submit URLs to urlscan.io — safety verdict + screenshot retrieval

Why use Urlscan on TypingMind?

Because you install it once and use it with any model. Urlscan is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Urlscan in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/taracodlabs/aiden/tree/main/skills/urlscan. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Urlscan?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Urlscan?

As many as you like. As long as a model supports skills, you can use Urlscan with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Urlscan AI skill free?

Yes. It is published on GitHub by taracodlabs under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇