ts-modern

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

• Third-party content exposure detected (high risk: 0.85). The required workflow explicitly instructs runtime web-search and fetching of public documentation pages (e.g., “Fetch https://docs.medusajs.com/...”), which are outsider-authored free text that 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: 1.00). The skill explicitly instructs the agent at runtime to fetch live docs (e.g., https://docs.medusajs.com/learn/fundamentals/modules/service-factory) and use those remote pages to determine exact types/generic signatures, meaning external content would directly control the agent's prompt/context for code generation.