design-tokens-skill

Warn

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed as a pointer that fetches a full version of itself from a remote GitHub repository (github.com/ilikescience/design-tokens-skill) which is not an established trusted source.
  • [REMOTE_CODE_EXECUTION]: The instructions direct the agent to use npx skills add to download and install a community-provided skill. This involves executing logic from the skills package and the remote repository to install code on the user's system.
  • [COMMAND_EXECUTION]: The skill provides logic for the agent to execute shell commands, such as grep and filesystem presence checks ([ -e ... ]), to determine the installation environment and scope.
  • [COMMAND_EXECUTION]: The documentation encourages the agent to utilize platform-specific execution shortcuts (prefixing commands with !) to automate the installation of third-party software within the chat session.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 10:45 AM
Security Audit — agent-trust-hub — design-tokens-skill