Cveapi logo

Cveapi

Organization
taracodlabs
cveapi

CVE lookup via MITRE + NVD: severity, CVSS, affected products, refs

Overview

Publishertaracodlabs
Repositoryaiden
Skill namecveapi
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 Cveapi 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/cveapi
  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/cveapi .claude/skills/cveapi
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cveapi 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 Cveapi 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 Cveapi 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.

CVE API — Vulnerability Lookup

Look up any CVE (Common Vulnerabilities and Exposures) by ID to get severity, CVSS score, affected products, and reference links. Uses the MITRE CVE API (cveawg.mitre.org) with automatic fallback to the NVD (National Vulnerability Database) for richer data.

No API key required. Optionally set NVD_API_KEY for higher rate limits on the NVD endpoint.

When to Use

  • User asks about a specific CVE by ID (e.g. "what is CVE-2021-44228?")
  • Security team needs severity and CVSS score for patch prioritization
  • Incident response: quickly triage whether a reported CVE is critical
  • Compliance audit: confirm affected software versions for a given vulnerability
  • User asks "is this CVE critical?", "what does CVE-XXXX-XXXXX affect?"

How to Use

Look up a single CVE (MITRE CVE API)

powershell
$cveId = "CVE-2021-44228"
$url   = "https://cveawg.mitre.org/api/cve/$cveId"

$result = Invoke-RestMethod -Uri $url
$cna    = $result.containers.cna
$desc   = ($cna.descriptions | Where-Object { $_.lang -eq 'en' } | Select-Object -First 1).value
$cvss   = $cna.metrics | ForEach-Object {
    $_.PSObject.Properties | Where-Object { $_.Name -like 'cvssV3*' } |
    Select-Object -First 1 -ExpandProperty Value
} | Select-Object -First 1

Write-Host "CVE:          $($result.cveMetadata.cveId)"
Write-Host "State:        $($result.cveMetadata.state)"
Write-Host "Published:    $($result.cveMetadata.datePublished)"
Write-Host "Score:        $($cvss.baseScore) ($($cvss.baseSeverity))"
Write-Host "Description:  $desc"
Write-Host "References:   $(($cna.references | Select-Object -First 3 -ExpandProperty url) -join ', ')"

Look up via NVD (richer data, optional API key)

powershell
$cveId   = "CVE-2021-44228"
$headers = @{}
if ($env:NVD_API_KEY) { $headers['apiKey'] = $env:NVD_API_KEY }

$url    = "https://services.nvd.nist.gov/rest/json/cves/2.0?cveId=$cveId"
$result = Invoke-RestMethod -Uri $url -Headers $headers
$cve    = $result.vulnerabilities[0].cve
$desc   = ($cve.descriptions | Where-Object { $_.lang -eq 'en' } | Select-Object -First 1).value
$metric = $cve.metrics.cvssMetricV31[0].cvssData

Write-Host "CVE:       $($cve.id)"
Write-Host "Published: $($cve.published)"
Write-Host "Score:     $($metric.baseScore) ($($metric.baseSeverity))"
Write-Host "Vector:    $($metric.vectorString)"
Write-Host "Desc:      $($desc.Substring(0, [Math]::Min(200, $desc.Length)))..."

Batch lookup — check multiple CVEs

powershell
$cveIds = @("CVE-2021-44228", "CVE-2023-4863", "CVE-2024-3094")

foreach ($id in $cveIds) {
    try {
        $url    = "https://cveawg.mitre.org/api/cve/$id"
        $result = Invoke-RestMethod -Uri $url
        $cna    = $result.containers.cna
        $cvss   = ($cna.metrics | Where-Object { $_.PSObject.Properties.Name -like 'cvssV3*' } |
                   Select-Object -First 1).PSObject.Properties.Value | Select-Object -First 1
        Write-Host "$id  Score: $($cvss.baseScore ?? 'N/A')  ($($cvss.baseSeverity ?? 'UNKNOWN'))"
    } catch {
        Write-Host "$id  ERROR: $($_.Exception.Message)"
    }
    Start-Sleep -Milliseconds 200   # polite rate limiting
}

Examples

"Look up CVE-2021-44228" → Returns Log4Shell details: CVSS 10.0 CRITICAL, affects Apache Log4j 2.x.

"What's the severity of CVE-2023-4863?" → Returns WebP heap buffer overflow: CVSS 8.8 HIGH, affects Chrome/libwebp.

"Get details for CVE-2024-3094" → Returns XZ Utils backdoor: CVSS 10.0 CRITICAL, supply-chain attack.

"Is CVE-2024-12345 critical?" → Looks up and reports severity tier: CRITICAL / HIGH / MEDIUM / LOW / NONE.

Cautions

  • MITRE CVE API has no documented rate limit — use 1–2 req/sec as a courtesy
  • NVD has stricter rate limiting: 5 req/30s without a key, 50 req/30s with NVD_API_KEY
  • Some CVEs are RESERVED (not yet disclosed) — the API returns limited data
  • CVSS score may be absent for very new or disputed CVEs
  • NVD and MITRE may have slightly different data — NVD is generally more complete

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 Cveapi AI skill do?

CVE lookup via MITRE + NVD: severity, CVSS, affected products, refs

Why use Cveapi on TypingMind?

Because you install it once and use it with any model. Cveapi 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 Cveapi in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/taracodlabs/aiden/tree/main/skills/cveapi. 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 Cveapi?

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 Cveapi?

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

Is the Cveapi 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 👇