shopify-development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were detected. The skill uses benign instructional language focused on development tasks.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file paths (e.g., .ssh, .aws) were found. The skill explicitly advises users to store API credentials in environment variables and verify webhook HMAC signatures.
  • [External Downloads] (SAFE): References the official @shopify/cli package via NPM. While not on the specific 'Trusted' list provided in the instructions, it is the official industry-standard tool for the claimed purpose.
  • [Indirect Prompt Injection] (LOW): The skill handles merchant-controlled data such as product titles and order names via GraphQL. While this presents an injection surface, the provided Liquid templates demonstrate the use of the | escape filter to mitigate basic script injection.
  • [Command Execution] (SAFE): CLI commands listed (shopify app dev, shopify theme init) are standard operations for Shopify development and do not include obfuscated or malicious parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM