expo-examples

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text from the public GitHub repository expo/examples via commands like gh api .../contents and fetching example files/trees (e.g., README/code) before adaptation.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes explicit runtime commands that fetch/clone remote code which could be read into the agent context or executed (curl https://raw.githubusercontent.com/expo/examples/master/with-stripe/utils/stripe-server.ts and git clone https://github.com/expo/examples.git), so it depends on external content at runtime.