nuxt-protokit

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to synchronize application state with a server endpoint. While it defaults to a relative path on the host server (/api/yjs), it allows configuration of external base URLs for synchronization via the Y.js protocol to maintain state across different clients.
  • [INDIRECT_PROMPT_INJECTION]: The skill architecture creates a surface for indirect prompt injection by ingesting and rendering user-defined data within schemas and collections.
  • Ingestion points: Untrusted data can enter the system through PrototypeSchema fields and CollectionSchema items as described in references/schema.md and SKILL.md.
  • Boundary markers: Data and instructions are separated by the component-based architecture of the Nuxt framework rather than explicit text-based delimiters.
  • Capability inventory: The skill has the capability to render data in various UI components (e.g., <ProtoDashboard>, <ProtoViz>) and export data into files via the export-markdown action.
  • Sanitization: Data is processed through Vue 3's reactive bindings, which provide default sanitization and escaping for content rendered in the user interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 08:04 AM