shopify-admin-agentic-readiness-audit

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). At runtime the skill ingests outsider-authored free text from the Shopify store’s own theme files (e.g., assets/llms.txt and templates/robots.txt.liquid) via the themes GraphQL query, and also ingests product HTML/metadata authored by the store (descriptions, alt text, metafield values) via the products/files queries; this content is not authored by the operating user and is fed into the agent’s LLM context for scoring.