building-inferencesh-apps

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

• Third-party content exposure detected (high risk: 0.90). The skill's docs explicitly show downloading and processing arbitrary URLs (e.g., File.from in references/node-app-logic.md), calling external APIs in the API-wrapper example (SKILL.md), and pulling models via huggingface_hub.snapshot_download (references/python-patterns.md), meaning untrusted third-party content is fetched and consumed as part of normal workflows and could therefore influence app behavior.