The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx to interact with the getdesign utility.
[REMOTE_CODE_EXECUTION]: The skill uses npx getdesign@latest to download and execute code from the public npm registry at runtime. Executing unversioned packages from a public registry allows for the execution of unverified remote code.
[EXTERNAL_DOWNLOADS]: The skill downloads brand-specific design system documentation (DESIGN.md) from the external domain getdesign.md.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted external documentation.
Ingestion points: External Markdown files are downloaded into the project directory from getdesign.md using the add command.
Boundary markers: The skill does not define boundary markers or provide instructions to ignore embedded commands when the agent reads the downloaded documentation.
Capability inventory: The skill environment allows shell command execution (npx) and file system writes.
Sanitization: There is no validation or sanitization of the downloaded content before the agent is prompted to 'Analyze design specifications' and 'Read DESIGN.md'.

byted-util-getdesign-md