The Agent Skills Directory

[SAFE]: The skill is entirely composed of informational markdown files providing guidelines on design system architecture and organizational adoption. No malicious instructions or suspicious code patterns were detected.\n- [PROMPT_INJECTION]: A thorough scan of the instructions and metadata revealed no attempts to bypass safety filters, override agent behavior, or extract system prompts. The language used is strictly professional and educational.\n- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file path references (e.g., .ssh, .aws), or network exfiltration patterns were found. The skill does not perform any data-gathering operations.\n- [REMOTE_CODE_EXECUTION]: While the documentation mentions several industry-standard development tools (e.g., Storybook, Style Dictionary), it does not include commands to download or execute unverified scripts. There are no 'curl | bash' or similar dangerous patterns.\n- [OBFUSCATION]: All analyzed files are written in clear, plain-text markdown. No Base64-encoded strings, zero-width characters, or homoglyph substitutions were detected.\n- [COMMAND_EXECUTION]: The skill does not instruct the agent to run dangerous shell commands. Mentions of CLI tools are provided as conceptual examples within a development workflow.

building-design-systems