nuxt

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

• Third-party content exposure detected (high risk: 0.70). The skill documentation (references/advanced-layers.md) explicitly shows using "extends: ['github:username/repo', 'gitlab:username/repo', ...]" to pull layers from public Git repositories, which are untrusted, user-generated third‑party sources that would be fetched/ingested and can materially alter build/runtime behavior.