shopify

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the user to paste the Shopify Admin API access token into the conversation and to run a command like ruby .../save_token.rb 'STORE' 'TOKEN', requiring the LLM to accept and/or emit the secret verbatim (CLI argument), which is direct secret exposure.

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

• Third-party content exposure detected (high risk: 0.70). The skill fetches and displays user-generated content from a third-party Shopify store via the Admin API (e.g., product body_html from /products/{id}.json and data from /customers.json, /orders.json shown in scripts and the SKILL.md flow), and the agent is instructed to read those responses and use them to decide or perform follow-up actions (e.g., show product details before updates), so untrusted store content could materially influence behavior.