Shopify JSON-LD Parser

Parse JSON-LD structured data from Shopify product pages to extract commerce details like product info, offers (price, currency, availability), and inventory...

Security Scan

The skill is internally coherent: its description, runtime instructions, and included parser script all align and there are no unexpected network calls, credential requests, or installation steps.

Purpose & Capability

Name/description promise is to extract schema.org/Product and Offer data from HTML. The SKILL.md and the included Python script implement exactly that and nothing extra (parsing <script type="application/ld+json">, extracting product fields and offers). No unrelated binaries, env vars, or services are requested.

Instruction Scope

Instructions restrict work to fetching/reading HTML and running the bundled script. They do not ask the agent to read unrelated system files or transmit data externally. One minor inconsistency: the SKILL.md shows an exec path 'skills/shopify-jsonld-parser/scripts/...' which assumes a specific working tree layout; it’s not a security issue but may require path adjustment. Also the script only handles static HTML (SKILL.md notes this) and takes the first Product found.

Install Mechanism

No install spec is provided (instruction-only + a small included script). Nothing is downloaded or installed from external URLs, so there is low install risk.

Credentials

The skill requires no environment variables, credentials, or config paths. The Python script reads local HTML files or (attempts to) read stdin; there are no requests for unrelated secrets or network endpoints.

Persistence & Privilege

Skill has no special persistence flags (always:false). It does not modify other skills or system settings. Autonomous invocation is allowed by default but combined with the limited scope here this is not a special risk.

Assessment

This skill appears to do exactly what it claims: parse JSON-LD from static Shopify HTML and return product/offer information. There are no network calls or secret requests in the code. Before installing or running: (1) test it on non-sensitive HTML samples — the script reads local files, so don’t point it at files containing credentials or private data; (2) note the script only handles static HTML (no JS-rendered content) and selects the first Product it finds; (3) the stdin fallback in the script is buggy (it tries to treat stdin content as a filename) — expect to pass a file path rather than piping raw HTML; and (4) if you need to run this at scale or inside an agent, validate the exec path shown in SKILL.md matches your runtime layout. If you want stronger assurance, ask the publisher for source provenance or run the script in an isolated environment.

Parse JSON-LD from Shopify product pages (or any schema.org/Product JSON-LD) to extract structured commerce data reliably.

Quick Start

1. Fetch HTML: web_fetch a product page URL.
2. Parse: Run scripts/parse_shopify_jsonld.py input.html (outputs JSON).
3. Query output for offers, availability, etc.

Example:

exec command="python3 skills/shopify-jsonld-parser/scripts/parse_shopify_jsonld.py page.html"

Workflow

1. Input: HTML file/path with JSON-LD (from web_fetch, read, or local).
2. Find JSON-LD: Script extracts all <script type="application/ld+json"> contents.
3. Parse Product: Traverse @graph or root for @type: Product, extract:
   • name, description, image, sku, brand
   • offers: array of Offer objects → price, priceCurrency, availability, url, itemCondition
   • availability (product-level or per-offer): http://schema.org/InStock, OutOfStock, PreOrder, etc.
   • Variants: Infer from multiple offers or hasVariant.
4. Output: Clean JSON: {product: {...}, offers: [...], inventory_status: "InStock|OutOfStock|Limited|Unknown"}

Inventory is typically availability enum, not exact quantity (use Shopify API for levels). Map:

• InStock → available
• OutOfStock → unavailable
• PreOrder/BackOrder → preorder

Usage Examples

Extract offers from page:

read path="shopify-page.html" → html
write path="tmp.html" content=html
exec command="python3 skills/shopify-jsonld-parser/scripts/parse_shopify_jsonld.py tmp.html" → parsed.json
read path="parsed.json"

Query CLI-style: Add --query price or --field offers[0].availability flags to script.

Script Reference

scripts/parse_shopify_jsonld.py [input.html] [--query FIELD] [--output json|yaml]

• Handles malformed JSON-LD gracefully.
• Supports multiple @graph items.
• Validates schema.org types.

Schema Reference

See references/schema.md for schema.org/Product + Offer properties.

Troubleshooting

• No JSON-LD: Returns {error: "No product JSON-LD found"}
• Multiple products: Takes first @type:Product.
• Dynamic Liquid: Static HTML only (no JS-rendered).