agent-sdk-streaming
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official Anthropic AI agent SDK (@anthropic-ai/claude-agent-sdk) for core streaming and interaction logic.
- [SAFE]: The provided code snippets demonstrate industry-standard implementation patterns for Server-Sent Events (SSE), frontend state management via React hooks, and proper request cancellation using AbortController. No malicious code, exfiltration patterns, or obfuscation techniques were identified.
Audit Metadata