Expo UI SwiftUI

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required workflow instructs the agent to fetch Expo documentation pages from https://docs.expo.dev/... at runtime; those fetched public web pages are outsider-authored free text that can be ingested into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill explicitly instructs the agent to fetch external documentation at runtime to determine component APIs (e.g., https://docs.expo.dev/versions/v55.0.0/sdk/ui/swift-ui/{component-name}/index.md and https://docs.expo.dev/versions/v55.0.0/sdk/ui/swift-ui/modifiers/index.md), so remote content would directly control the agent's behavior.