claude-code-agent-sdk
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation repository for the Claude Agent SDK. The contents are exclusively markdown files and code examples that follow industry-standard security practices.
- [SAFE]: All network-related examples (e.g., OTLP endpoints, MCP server URLs) use placeholders or reference official, well-known services (like Anthropic APIs and official GitHub repositories).
- [SAFE]: No obfuscation, prompt injection, or persistent mechanisms were found in the skill body or metadata.
- [SAFE]: The documentation explicitly includes guidance on isolation, credential management, and the principle of least privilege for production deployments.
Audit Metadata