shopify-liquid

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly fetches public web content at runtime from https://shopify.dev/docs/api/liquid and via web-search results, and that fetched page text is read by the agent to inform the LLM context (outsider-authored public web content).

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to fetch live documentation from https://shopify.dev/docs/api/liquid at runtime to inform template generation, which means remote content would directly control the agent's prompts/instructions and is treated as a required dependency.