moai-lang-swift

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests external documentation and web content (via Context7 MCP get_library_docs and example URLSession calls to public endpoints like jsonplaceholder.typicode.com and references to Swift Forums), so the agent will read third‑party/public (including user‑generated) content as part of its workflow, enabling potential indirect prompt injection.