The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to run npx ui-skills get <slug> to download and execute the ui-skills package from the npm registry. This represents execution of external, unverified code in the agent's environment.
[EXTERNAL_DOWNLOADS]: Fetches specialist design lenses and resources from the npm registry using the npx command.
[COMMAND_EXECUTION]: Automatically executes shell commands to interact with the external ui-skills tool and list available categories via npx ui-skills list.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain malicious instructions.
Ingestion points: The agent reads content from meta/DESIGN.md and Markdown documentation returned by the npx ui-skills command.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this external content as untrusted data or to ignore embedded commands.
Capability inventory: The skill possesses the capability to execute shell commands via npx, write files to the local filesystem (meta/design-critiques/), and dispatch subagents.
Sanitization: The skill lacks logic to validate or sanitize the fetched Markdown content before it is used to influence the critique logic.

design-critique