shopgraph — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited shopgraph (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill when you need to extract structured product information (title, price, brand, description, images, availability, categories) from any e-commerce URL or raw HTML.
Connect to ShopGraph's remote MCP server:
{
"mcpServers": {
"shopgraph": {
"url": "https://shopgraph.dev/mcp"
}
}
}Or install locally via npm:
{
"mcpServers": {
"shopgraph": {
"command": "node",
"args": ["node_modules/shopgraph/dist/index.js"]
}
}
}Full AI-powered product extraction from a URL. Schema.org first, Gemini LLM fallback, optional Playwright browser rendering. Returns structured data with per-field confidence scores.
Schema.org extraction only. Fast, no AI cost. Good for sites with proper structured data markup.
Extract product data from raw HTML. Use when you already have the page content.
strict_confidence_threshold (0.0-1.0): Scrub fields below this confidence to null with explanation. Useful for high-stakes pipelines.format ("default" | "ucp"): Return UCP-compatible line_item format for commerce protocol compliance.enrich_basic to check if Schema.org data exists (free)enrich_product for AI extractionenrich_html when working with pre-fetched HTML contentstrict_confidence_threshold=0.80 for production pipelines that need high-reliability dataAuthorization: Bearer sg_live_... header for subscription tierspayment_method_id for per-call Stripe paymentsReturns ProductData with:
_shopgraph.field_confidence — per-field confidence scores (0.0-1.0)_shopgraph.confidence_method — scoring mechanism usedWebsite: https://shopgraph.dev
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.