shopify-development

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting data from external APIs and providing powerful local capabilities.
  • Ingestion points: Data enters the agent's context through scripts/shopify_graphql.py via the Shopify GraphQL Admin API.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the API response processing logic.
  • Capability inventory: The skill can execute shell commands via the shopify CLI (in scripts/shopify_init.py), perform network operations to any *.myshopify.com domain (in scripts/shopify_graphql.py), and write configuration files to the local filesystem (in scripts/shopify_init.py).
  • Sanitization: The skill lacks explicit sanitization or validation of the content retrieved from the GraphQL API before it is presented to the AI or used to influence project scaffolding.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 06:04 AM