lesson-screen

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors clicks and interactive events submitted by learners via the local web server endpoint /event, which ingests user-submitted free text (such as custom choice text, question responses, and notes) that the agent subsequently reads via CLI events before each reply.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references optional external assets from https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/ under third-party unofficial user namespace provenance.