shopify-admin-agentic-description-enrichment

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill ingests and processes product-related data from an external Shopify store to generate new descriptions.
  • Ingestion points: Step 1 in SKILL.md retrieves descriptionHtml, title, tags, and metafields from the products query.
  • Boundary markers: The instructions do not define clear delimiters or include guidance for the agent to ignore instructions embedded within the product data.
  • Capability inventory: The skill has the capability to modify store content via the productUpdate mutation.
  • Sanitization: There is no mention of sanitizing or validating the ingested content before it is processed in the COMPUTE step.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:05 AM
Security Audit — agent-trust-hub — shopify-admin-agentic-description-enrichment