Scaffold a Vue 3.5+ project with Composition API (`<script setup>`), Pinia stores, Vue Router 4, TypeScript, Vite, and auto-imports via unplugin.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Third-party content exposure detected (high risk: 0.80). The skill includes a reusable fetch composable (src/shared/composables/useFetch.ts) shown in SKILL.md that calls fetch() on arbitrary URLs and returns JSON which is consumed by stores/components (e.g., store.fetchUsers, the auth store used by the router guard), so untrusted third-party content could be ingested and materially influence app behavior.
181fcbc
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.