privatelm-cross-platform-llm-client

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly downloads and loads arbitrary model files from external URLs (lib/controllers/model_controller.dart: downloadModel) and streams outputs from third‑party cloud LLM APIs (lib/services/cloud_service.dart: generateOpenAI/generateClaude/generateGemini), both of which ingest untrusted external content that is then executed/used for inference and can materially influence subsequent actions and decisions.