mcp-app-dev-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly asks the agent to obtain cluster credentials from the user/1Password and populate/use them in a .env file and validation commands, which requires handling and potentially embedding secret values verbatim.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs "git clone https://github.com/elastic/forge.git ../forge" and then installs and executes code from that repository (pip install -e ".[dev]" and python3 -m forge.cli), so the external GitHub repo is fetched at runtime and its code is executed as a required dependency.