deepagents-subagents
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation guide for using
SubAgentMiddlewarewithin thedeepagentsframework. All code examples use standard JavaScript/TypeScript patterns and reputable libraries. - [SAFE]: External links point to the official LangChain documentation (
docs.langchain.com), which is a well-known and trusted source for AI developer resources. - [SAFE]: The library dependencies identified (
deepagents,langchain,zod,@langchain/langgraph) are established packages in the AI development community. - [SAFE]: No prompt injection, data exfiltration, or obfuscation patterns were detected in the instructions or code snippets.
Audit Metadata