claude-code-expert
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a documentation and configuration guide for the official Claude Code CLI by Anthropic. It contains no executable malicious code or instructions to bypass safety protocols.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the official
@anthropic-ai/claude-codepackage via npm. This is a reference to a well-known service and a trusted organization, following standard developer workflows. - [COMMAND_EXECUTION]: Numerous examples of shell commands and automation hooks are provided. These are strictly instructional and include explicit warnings against using dangerous flags like
--dangerously-skip-permissionsin production or sensitive environments. - [CREDENTIALS_UNSAFE]: While the skill mentions environment variables such as
ANTHROPIC_API_KEY, it correctly uses placeholders (e.g.,sk-ant-SUA_CHAVE_AQUI) and does not contain any hardcoded secrets or sensitive credentials.
Audit Metadata