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.pyvia 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
shopifyCLI (inscripts/shopify_init.py), perform network operations to any*.myshopify.comdomain (inscripts/shopify_graphql.py), and write configuration files to the local filesystem (inscripts/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