high-risk-order-tagger

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to perform authentication via the official Shopify CLI (shopify store auth). This is a standard and expected administrative procedure for Shopify store management.
  • [DATA_EXPOSURE]: The skill queries sensitive store data, including order details, pricing, and customer information (IDs, display names). This access is necessary for the stated purpose of fraud risk assessment and tagging.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from an external source (Shopify order and customer fields).
  • Ingestion points: Data enters the agent context via the orders GraphQL query in SKILL.md.
  • Boundary markers: None identified between external data and agent instructions.
  • Capability inventory: The skill performs write operations using tagsAdd and fulfillmentOrderHold mutations.
  • Sanitization: No specific sanitization or validation of the fetched data is described before it is processed or used in subsequent mutation inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 04:14 AM