shopify-core-workflow-b
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Shopify Admin API, creating a potential surface for indirect prompt injection if external data (e.g., customer notes, order names, or line item titles) contains malicious instructions intended for the agent.
- Ingestion points: Data is fetched via GraphQL queries in
references/query-orders.mdandreferences/customer-search-query.md. - Boundary markers: None explicitly defined in the reference snippets to distinguish between instructions and API data.
- Capability inventory: The skill has access to
Read,Write,Edit,Bash(npm:*), andGreptools as specified inSKILL.mdfrontmatter. - Sanitization: No specific sanitization or validation logic is shown in the provided GraphQL templates.
Audit Metadata