shopify-themes

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes “Fetch live docs” and “Web-search” steps (e.g., fetching https://shopify.dev/... and searching GitHub/Shopify pages) which are public web content that can be ingested as readable text into the agent’s LLM context, creating an indirect prompt-injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to "Fetch live docs" including https://shopify.dev/docs/storefronts/themes and the Dawn repository https://github.com/Shopify/dawn to drive how the agent writes code and follows schema/patterns, meaning external content would directly control the agent's prompts and behavior.