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 using the Claude API via Anthropic's official SDKs. It contains code snippets for message creation, streaming, vision, and tool use, all of which are standard API implementation patterns.
- [CREDENTIALS_UNSAFE]: The skill correctly identifies credential management as a security concern, explicitly stating 'Never hardcode API keys. Always use environment variables.' and providing examples that read from the environment (
client = anthropic.Anthropic()). It uses the placeholderyour-api-key-herefor documentation purposes only. - [EXTERNAL_DOWNLOADS]: The skill references official and well-known packages
anthropic(PyPI) and@anthropic-ai/sdk(npm) for installation. These are standard dependencies for the described functionality. - [COMMAND_EXECUTION]: Shell commands are restricted to standard package installation (
pip install,npm install) and setting environment variables (export), which are appropriate for a developer documentation skill.
Audit Metadata