data-fetching-patterns

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

• Third-party content exposure detected (high risk: 0.80). The skill includes runtime code that fetches and parses data from arbitrary URLs and event streams (e.g., streamJSON(url), createSSEConnection(url)/EventSource, generic fetch()/getResource() and useStreamingData(url) examples), which would ingest untrusted public/user-generated content that the agent is expected to read and render.