shopify-admin-order-lookup-and-summary
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface in the way it handles search parameters. * Ingestion points: Untrusted input is accepted via the
lookup_valueparameter in the SKILL.md definition. * Boundary markers: There are no explicit delimiters (e.g., XML-like tags) or instructions provided to the agent to isolate the user input from the rest of the logic. * Capability inventory: The skill uses theorders:querycapability via theshopify-admintoolkit to retrieve sensitive customer personally identifiable information (PII), including addresses and contact details. * Sanitization: No validation or sanitization is performed on the lookup value before it is interpolated into the GraphQL query.
Audit Metadata