shopify-products

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes examples that place the Admin API access token directly into HTTP headers/CLI commands (e.g., curl -H "X-Shopify-Access-Token: {token}"), which requires the LLM to insert or handle the secret verbatim rather than use environment-based or internal auth, creating exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts "Website scraping (user provides a URL to extract from)" in Step 1 and allows using public image URLs (Image Src / "pass src directly"), so the agent will fetch and interpret arbitrary public web content to populate products and drive API/CSV import actions.