The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to manage its workflow and process external data. Specifically, it executes cd /tmp && mkdir -p design-md-tmp && cd design-md-tmp && npx getdesign@latest add <slug> 2>&1 to handle design assets. It also uses the open command to automatically launch generated HTML files for user preview. There is a potential risk of command injection if the <slug> variable, which is dynamically retrieved based on user brand requests, is not properly sanitized before being passed to the shell.
[EXTERNAL_DOWNLOADS]: The skill is configured to download external code at runtime. The command npx getdesign@latest fetches the getdesign package directly from the public NPM registry. This introduces a dependency on an external, third-party source that is not listed as a trusted vendor.
[REMOTE_CODE_EXECUTION]: The use of the npx command pattern leads to remote code execution. By downloading and immediately executing a package from a public registry, the skill runs arbitrary code provided by the package maintainers. The use of the @latest tag ensures the most recent version is always executed, which increases exposure to potential supply chain attacks if the package or its account is compromised.

space-chart-html-plus