ui-design

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch external documentation from a designated GitHub URL using WebFetch, exposing it to repository content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to fetch remote instructions from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md during runtime and apply them directly.