claude-code-operator
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the installation of
@anthropic-ai/claude-code, which is the official package from a trusted organization. - [DATA_EXFILTRATION]: The skill demonstrates sending content (HTML) to an external MCP server endpoint (
https://mcp-on-edge.edgeone.app/mcp-server). This is documented as a primary function for project deployment to Tencent's EdgeOne service, which is a well-known cloud infrastructure provider. - [CREDENTIALS_UNSAFE]: The skill provides instructions for managing API keys via environment variables and configuration files, correctly utilizing placeholders (
YOUR_ZHIPU_API_KEY_HERE) to avoid hardcoding secrets. - [COMMAND_EXECUTION]: The skill provides workflows for executing the
claudeCLI and includes a bash setup script for environment configuration. These operations are consistent with the intended purpose of a developer-focused operator skill.
Audit Metadata