The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads content from an external repository (https://github.com/voltagent/awesome-design-md) during the setup phase.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including mkdir, git clone, and git pull to manage its local cache of design references in the ${CLAUDE_PLUGIN_DATA} directory.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the cloned repository which could contain malicious instructions.
Ingestion points: The agent is instructed to read DESIGN.md, README.md, and HTML preview files (preview.html, preview-dark.html) from the downloaded repository.
Boundary markers: No delimiters or warnings are provided to help the agent distinguish between legitimate design tokens and potentially malicious instructions embedded in the external files.
Capability inventory: The agent has the ability to read local files, execute git commands for updates, and generate UI code based on the ingested data.
Sanitization: There is no indication that the external content is validated, sanitized, or filtered before the agent uses it to generate code or provide advice.

awesome-design