expo-examples

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is fetched at runtime from the public expo/examples GitHub repo (e.g., via gh api .../trees/... and .../contents/<example>/<file> or curl raw URLs), and that README/code/text is then ingested into the agent’s LLM context for study/adaptation.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs runtime fetching of example code from the Expo examples repository (e.g. https://github.com/expo/examples and raw file URLs such as https://raw.githubusercontent.com/expo/examples/master/with-stripe/utils/stripe-server.ts via gh api / curl) and also suggests running tools like npx create-expo/degit that execute fetched packages — these are used at runtime and can inject remote content into the agent context or execute remote code.