miniapp-design

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes structured design documentation to generate application code, creating an attack surface for indirect prompt injection.
  • Ingestion points: Reads content from apps/teamventure/docs/design/miniapp-pages-obsidian.md and design tokens from apps/teamventure/design/tokens/*.json.
  • Boundary markers: None identified. The instructions do not define specific delimiters or instructions to ignore embedded prompts within the design documents.
  • Capability inventory: The skill is designed to read and modify project files including WXML, WXSS, and JavaScript logic (apps/teamventure/src/frontend/miniapp/pages/).
  • Sanitization: None identified. The agent is instructed to follow the design descriptions directly when generating logic and structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 01:48 AM