shopify
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of
curlandjqto interact with Shopify's Admin and Storefront GraphQL endpoints. These commands are standard for API interaction and intended for technical users and agents. - [DATA_EXPOSURE]: The skill requires a
SHOPIFY_ACCESS_TOKENand store domain. It correctly advises the user to store these credentials in a local.envfile and use environment variables, which is a standard security best practice for managing secrets. - [EXTERNAL_DOWNLOADS]: Includes instructions for the Shopify Bulk Operations API, which involves downloading JSONL files from URLs generated by the Shopify platform. This is a legitimate feature of the service.
- [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection because it instructs the agent to read and process data from external Shopify stores (such as product descriptions and order notes). If these fields contain malicious instructions, the agent could potentially be influenced by them. This is a inherent risk of tools that process external content and is mitigated by the agent's internal safety guardrails.
Audit Metadata