cpbox-images-search

USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.

Security Scan

The skill's declared purpose (image search) matches its runtime instructions, but the SKILL.md requires an external pay-per-use flow and SDKs without declaring any credentials or setup details in the manifest — this mismatch warrants caution.

Purpose & Capability

The name and description (image search, thumbnails, safesearch, up to 200 results) match the SKILL.md, which documents a dedicated images-search API on https://www.cpbox.io and output schema appropriate for image search.

Instruction Scope

The instructions direct the agent to call an external API (cpbox.io) that uses a payment protocol (x402) and refer to installing/using payment tooling (npx @springmint/x402-payment or x402-sdk-go). The SKILL.md also references prerequisite setup steps in a README at a relative path (../../README.md) that isn't included in the package. While calling an external paid API is consistent with the purpose, the payment flow and SDK usage broaden the runtime behavior beyond simple read-only image search and require trusting third-party tooling and networks.

Install Mechanism

This is instruction-only (no install spec, no code files). However, SKILL.md recommends invoking an npm package via npx or a Go SDK; that will pull and execute third-party code at runtime if used. The manifest does not ship or pin those packages.

Credentials

The manifest lists no required environment variables or credentials, but the SKILL.md explicitly requires completing x402-payment setup and signing requests (PAYMENT-SIGNATURE). That implies secret keys or payment credentials will be provided somewhere — the skill manifest does not declare or justify those secrets, creating a transparency gap about what credentials an agent or user must supply.

Persistence & Privilege

The skill does not request always: true, does not declare installs that write system-wide config, and is user-invocable only. It does allow normal autonomous invocation (platform default).

What to consider before installing

This skill appears to be a straightforward image-search proxy that charges per request. Before installing: (1) confirm how you will provide payment credentials and where they are stored — the manifest does not declare them, so check the README/setup referenced in SKILL.md; (2) review the reputations and privacy policies of https://www.cpbox.io and https://www.cppay.finance and the payment SDK (e.g., @springmint/x402-payment) since running npx will fetch third-party code at runtime; (3) avoid entering high-privilege keys until you verify the exact secrets required and how they are used; (4) test with minimal queries and monitor network/billing activity; and (5) if you need stronger assurances, request the README and any setup scripts from the skill author or prefer a skill that declares its required credentials explicitly in the manifest.

Images Search

Paid Images Search proxy via x402 pay-per-use (HTTP 402).

Prerequisites: This skill requires x402-payment. Complete the setup steps before first use.

Service URLs

Role	Domain
API Provider	https://www.cpbox.io
Facilitator	https://www.cppay.finance

Endpoint (Agent Interface)

GET /api/x402/images-search

Payment Flow (x402 Protocol)

1. First request -> 402 Payment Required with requirements JSON
2. Sign & retry with PAYMENT-SIGNATURE -> result JSON

With @springmint/x402-payment or x402-sdk-go, payment is automatic.

Quick Start (cURL)

Basic Search

curl -s "https://www.cpbox.io/api/x402/images-search?q=mountain+landscape" \
  -H "Accept: application/json"

With Parameters

curl -s "https://www.cpbox.io/api/x402/images-search" \
  -H "Accept: application/json" \
  -G \
  --data-urlencode "q=northern lights photography" \
  --data-urlencode "country=US" \
  --data-urlencode "search_lang=en" \
  --data-urlencode "count=20" \
  --data-urlencode "safesearch=strict"

Using with x402-payment

npx @springmint/x402-payment \
  --url "https://www.cpbox.io/api/x402/images-search?q=mountain+landscape&count=20" \
  --method GET

Parameters

Parameter	Type	Required	Default	Description
q	string	Yes	-	Search query (1-400 chars, max 50 words)
country	string	No	US	Search country (2-letter country code or ALL)
search_lang	string	No	en	2+ char language code
count	int	No	50	Results to return (1-200)
safesearch	string	No	strict	off or strict (no moderate for images)
spellcheck	bool	No	true	Auto-correct query; corrected query in query.altered

Response Format

{
  "type": "images",
  "query": {
    "original": "mountain landscape",
    "altered": null,
    "spellcheck_off": false,
    "show_strict_warning": false
  },
  "results": [
    {
      "type": "image_result",
      "title": "Beautiful Mountain Landscape",
      "url": "https://example.com/mountain-photo",
      "source": "example.com",
      "page_fetched": "2025-09-15T10:30:00Z",
      "thumbnail": {
        "src": "https://imgs.search.provider/...",
        "width": 200,
        "height": 150
      },
      "properties": {
        "url": "https://example.com/images/mountain.jpg",
        "placeholder": "https://imgs.search.provider/placeholder/...",
        "width": 1920,
        "height": 1080
      },
      "meta_url": {
        "scheme": "https",
        "netloc": "example.com",
        "hostname": "example.com",
        "favicon": "https://imgs.search.provider/favicon/...",
        "path": "/mountain-photo"
      },
      "confidence": "high"
    }
  ],
  "extra": {
    "might_be_offensive": false
  }
}

Response Fields

Field	Type	Description
type	string	Always "images"
query.original	string	Original query
query.altered	string?	Spellchecked query (null if no correction)
query.spellcheck_off	bool?	Whether spellcheck was disabled
query.show_strict_warning	bool?	True if strict safesearch hid relevant results
results[]	array	List of image results
results[].type	string	Always "image_result"
results[].title	string?	Image title
results[].url	string?	Page URL where image was found
results[].source	string?	Source domain
results[].page_fetched	string?	ISO datetime of last page crawl
results[].thumbnail.src	string?	Proxy-served thumbnail URL (~500px width)
results[].thumbnail.width	int?	Thumbnail width
results[].thumbnail.height	int?	Thumbnail height
results[].properties.url	string?	Original full-size image URL
results[].properties.placeholder	string?	Low-res placeholder URL (proxy-served)
results[].properties.width	int?	Original image width (may be null)
results[].properties.height	int?	Original image height (may be null)
results[].meta_url.scheme	string?	URL protocol scheme
results[].meta_url.netloc	string?	Network location
results[].meta_url.hostname	string?	Lowercased domain
results[].meta_url.favicon	string?	Favicon URL
results[].meta_url.path	string?	URL path
results[].confidence	string?	Relevance: low, medium, or high
extra.might_be_offensive	bool	Whether results may contain offensive content

Use Cases

• Visual content discovery: Build image galleries, mood boards, or visual research tools. Use count=200 for comprehensive coverage. Prefer over web-search when you need image-specific metadata (dimensions, thumbnails).
• Content enrichment: Add relevant images to articles or generated content. Use country and search_lang to target your audience's locale.
• Safe image retrieval: Default safesearch=strict ensures family-friendly results out of the box. Only two modes (off/strict) — no moderate option, unlike web/video/news search.
• High-volume batch retrieval: Up to 200 images per request (vs 20 for web, 50 for videos/news). Ideal for bulk image sourcing or visual analysis pipelines.

Notes

• SafeSearch: Defaults to strict for images (stricter than web search)
• High volume: Can return up to 200 results per request
• Thumbnails: Proxy-served for user privacy (500px width). Use properties.url for original full-resolution image.
• Dimensions: properties.width/height may be missing for some images
• Placeholder: properties.placeholder is a low-res URL (not inline base64) useful for progressive loading UX