Feature-Based-Layered-Architecture

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md "How to Use" section explicitly instructs running npx skills add with public GitHub URLs (e.g., https://github.com/supabase/agent-skills), which fetches and installs third‑party, user‑authored skill code from the open web that can alter agent behavior and thus could enable indirect injection of instructions.