learn

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

• Third-party content exposure detected (low risk: 0.10). At runtime the skill fetches lesson content (en.md) and quizzes (quiz.json) from the repository (locally or via a trusted GitHub raw URL) and does not ingest arbitrary outsider-authored free text without first selecting specific repo files.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly falls back to fetching lesson and quiz files at runtime from https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/, which directly supplies the lesson text and quiz content used to construct prompts and drive teaching, satisfying the criteria for a runtime external dependency that controls agent instructions.