shopify-admin-repeat-purchase-rate

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses personally identifiable information (PII) through the Shopify GraphQL API, specifically customer email addresses (emailAddress) and order history. This data is used to correlate repeat purchases and is exported to a local CSV file for the user. While this behavior is consistent with the skill's purpose, the access to PII should be noted.
  • [PROMPT_INJECTION]: The skill processes data from external sources (Shopify API) and is therefore susceptible to indirect prompt injection.
  • Ingestion points: External data enters the context via the customers:query and orders:query operations in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data values (like product titles or customer notes) and instructions.
  • Capability inventory: The skill uses the shopify-admin toolkit to execute GraphQL queries but does not perform any destructive mutations or shell command executions beyond standard CLI usage.
  • Sanitization: No explicit sanitization or filtering of API response data is described before the data is processed or included in the final CSV/JSON output.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 08:01 AM