shadcn

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow described in SKILL.md is the shadcn CLI fetching/searching/downloading component documentation/examples and registry item contents (public/web or community/GitHub registries) as readable file text, which can include outsider-authored free text/templates and get inserted into the agent context for review/view/diff.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to run the CLI and fetch external documentation/registry files at runtime (e.g. https://ui.shadcn.com/init?base=radix&style=nova&...), and those fetched remote docs/registry files would be used to drive the agent's component-generation instructions.