ai-engineering-curriculum

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

• Third-party content exposure detected (high risk: 0.75). Outsider source category: the skill’s runtime workflow fetches and ingests the external GitHub repository content (“rohitg00/ai-engineering-from-scratch” via npx skills add ...) as curriculum text to drive quizzes/recommendations, which is free-form outsider-authored material read into the agent’s LLM context.