react-native-ai-skills

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly downloads and runs community models from public repositories (e.g., downloadModel('owner/repo/model.gguf') in references/llama-provider.md and cloning GitHub in references/mlc-provider.md), meaning untrusted third-party model files are ingested and directly influence generated outputs.