shopify-metafields

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions and evaluation tasks involve processing external data sources (such as JSON files containing product attributes, FAQs, or testimonials) to generate and execute Shopify API mutations. This ingestion of external content creates a standard surface for indirect prompt injection if the source data contains instructions intended to manipulate the agent's behavior during the import process.
  • Ingestion points: External JSON data sources mentioned in the enrichment and content system tasks (e.g., inputs/products.json).
  • Boundary markers: The provided logic does not explicitly use delimiters or specific warnings to the agent to ignore instructions embedded within the data values.
  • Capability inventory: The skill utilizes Shopify Admin API mutations including metafieldDefinitionCreate, metafieldsSet, and metaobjectCreate to modify store data.
  • Sanitization: The examples demonstrate standard data mapping and JSON serialization, which is typical for this integration type, but they do not include specific sanitization for potential command or instruction injection within text fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:00 AM