lesson-screen

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches lesson content and files via fetch() from public GitHub (raw.githubusercontent.com) or clone repos when preparing practice pages or loading figure skills, allowing outsider-authored markdown/code to be ingested.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches figure templates from 'https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/skills//' under unverified and arbitrary community repository control, presenting a high-tier external dependency risk.