The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard shell commands like ls and cat to inspect project directories such as public/, assets/, and brand/, as well as configuration files like tailwind.config.*. These commands are used solely to gather design context for visual asset generation and are hardcoded, preventing user-controlled command injection.
[DATA_EXPOSURE]: The skill reads local design assets, theme documentation, and IDE rules (e.g., .cursor/rules/) to align new visual art with the existing brand identity. No network operations, external data requests, or exfiltration mechanisms are present.

design-canvas