claude-api
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a reference for building applications with the Claude API. It includes standard implementation patterns for streaming, tool use, and vision.
- [EXTERNAL_DOWNLOADS]: Documents the installation of official libraries:
anthropic(Python) and@anthropic-ai/sdk(Node.js). These are well-known packages from a trusted service provider. - [CREDENTIALS_UNSAFE]: Explicitly instructs the user to use environment variables for API keys and provides a warning against hardcoding credentials in code.
- [PROMPT_INJECTION]: No patterns detected that attempt to override agent instructions or safety filters.
Audit Metadata