shopify-gmc-misrepresentation-auditor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill explicitly crawls and fetches arbitrary public Shopify store and product pages (see fetchPage usage in scripts/gmc-store-audit.mjs and scripts/gmc-product-audit.mjs, plus sitemap/collections/product discovery and JSON-LD parsing) and directly reads/interprets that untrusted third-party content to drive checks, scoring, and follow-up actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires running the npx update command at runtime ("npx --yes skills update shopify-gmc-misrepresentation-auditor -g -y"), which will fetch and execute remote package code from the npm registry (e.g., https://registry.npmjs.org/shopify-gmc-misrepresentation-auditor) as a mandatory first step, so this is a runtime external dependency that executes remote code and is required.