expo-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires calling MCP to fetch external documentation (e.g., fetch_expo_sdk, fetch_tamagui_docs, fetch_npm_docs, fetch_ios_hig) and mandates the agent read and follow those public third‑party docs before implementing code, so untrusted web content can materially influence tool use and decisions.