medusa-pricing

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly performs runtime web-searches and fetches public documentation pages (e.g., “Web-search site:docs.medusajs.com …” and “Fetch https://docs.medusajs.com/…/pricing”), so the LLM ingests outsider-authored free text from public web content into its context.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs at runtime to fetch and use external documentation (https://docs.medusajs.com/resources/references/pricing), which would directly control the agent's implementation/prompting by loading remote instructions about the IPricingModuleService interface.