shopify-admin-vip-customer-identifier

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to its handling of external data without sanitization.
  • Ingestion points: Shopify customer records (names, email addresses, and tags) retrieved via the customers:query operation in SKILL.md.
  • Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent to ignore instructions that might be embedded within customer-controlled fields.
  • Capability inventory: The skill utilizes the customerUpdate mutation, allowing it to modify customer tags in the live Shopify store.
  • Sanitization: No sanitization, escaping, or validation of the data retrieved from Shopify is implemented before processing or re-uploading via mutation.
  • [DATA_EXPOSURE]: The skill accesses customer Personal Identifiable Information (PII), such as full names, email addresses, and purchase aggregates. This behavior is expected for its administrative purpose and the data is stored locally in a CSV file, representing a legitimate use case within the Shopify platform context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:05 AM
Security Audit — agent-trust-hub — shopify-admin-vip-customer-identifier