create-mcp-servers

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill executes local initialization scripts (setup-python-project.sh, setup-typescript-project.sh) and the claude mcp CLI. These are required for project setup and server registration. The troubleshooting guide suggests persisting environment variables in ~/.zshrc, which is a standard configuration step.
  • [EXTERNAL_DOWNLOADS] (LOW): Setup scripts install standard libraries (mcp, @modelcontextprotocol/sdk) and development tools from official registries (PyPI, npm). Per [TRUST-SCOPE-RULE], these are categorized as LOW risk.
  • [CREDENTIALS_UNSAFE] (SAFE): The skill mandates the use of environment variables and specifically warns against hardcoding secrets or sharing them in chat, adhering to security best practices.
  • [PROMPT_INJECTION] (SAFE): No prompt injection or behavior override patterns were detected. The skill uses well-defined instruction boundaries and natural language.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 11:53 PM