The Agent Skills Directory

[SAFE] (SAFE): The skill consists entirely of markdown instructions and metadata. It does not include any executable files (.sh, .py, .js), binaries, or configuration files that could trigger system-level actions.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process user-provided frontend requirements to generate code artifacts.
Ingestion points: User requirements provided in the chat context.
Boundary markers: None present in the instructions to separate user data from the system's design logic.
Capability inventory: The skill only generates code for display/output; it lacks the capability to write to the filesystem, execute subprocesses, or perform network requests.
Sanitization: No explicit sanitization or validation of user input is mentioned, but the lack of executable 'sinks' (like eval or exec) mitigates this risk to a negligible level.

frontend-design