The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The setup instructions in references/mcp.md direct the user/agent to execute a remote script directly in the shell using the curl | sh pattern. Specifically, it executes curl -fsSL https://tools.yshubham.com/sandbox/setup.sh | sh. This is a dangerous pattern as it executes unverified code from the internet with the user's local privileges.
[EXTERNAL_DOWNLOADS]: The skill downloads and installs software from tools.yshubham.com. This domain is an external source not associated with the skill's author metadata or known trusted repositories, posing a supply chain risk.
[COMMAND_EXECUTION]: The skill's primary functionality relies on executing a variety of shell commands through the sandbox CLI and sandbox-mcp binary, including environment variable exports that handle authentication tokens.

sandbox-platform