llm-streaming-response-handler

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

• Third-party content exposure detected (high risk: 0.80). This skill reads and displays streamed SSE responses from external endpoints—most directly via scripts/stream_tester.ts (which accepts arbitrary endpoints like https://api.example.com/stream) and client/server fetch/EventSource examples that parse and render incoming "data:" payloads—so untrusted third‑party content could inject instructions into the agent's workflow.