Skills
Navigate
skills/40rty-ai/shopify-admin-skills/shopify-admin-agentic-product-taxonomy/Gen Agent Trust Hub

shopify-admin-agentic-product-taxonomy

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is well-structured and uses official Shopify GraphQL operations (products, taxonomy, and productUpdate) to perform its intended task without any malicious intent or hidden behaviors.
  • [PROMPT_INJECTION]: Evaluated the surface for indirect prompt injection via product metadata processing.
  • Ingestion points: Product title, productType, and tags retrieved from the Shopify store in Step 1 of the workflow.
  • Boundary markers: Absent; there are no explicit delimiters used when processing product data for taxonomy matching.
  • Capability inventory: The skill has the ability to modify live store data using the productUpdate mutation in Step 4.
  • Sanitization: Risk is effectively mitigated through the use of a confidence_floor parameter (defaulting to 0.7) and a mandatory dry_run option to preview mutations before they are applied to live products.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:05 AM
Security Audit — agent-trust-hub — shopify-admin-agentic-product-taxonomy