spree-data-model

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text is fetched at runtime from public web pages (e.g., https://spreecommerce.org/docs/... and GitHub source) via the “Fetch live docs” steps, and that readable documentation content can be ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly directs the agent at runtime to fetch live docs from https://spreecommerce.org/docs/developer/core-concepts/architecture (and related spreecommerce.org docs listed) — these remote pages are required and used to guide the agent's prompts/implementation decisions, so they are runtime external dependencies that directly control the agent's instructions.