frontend-designer

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs use of shadcn CLI to install from remote registries (references/shadcn-patterns.md) and also permits consulting live docs / WebSearch (SKILL.md "Live Documentation"), so the agent will fetch and act on open third‑party content that can influence decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs runtime use of the shadcn CLI which can fetch and install registry items from remote URLs (e.g., "https://example.com/r/custom-widget.json") — a runtime fetch that injects remote component source into the project and effectively executes/introduces external code, so it directly controls the agent's runtime behavior.