llm-from-scratch-guide

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

• Third-party content exposure detected (high risk: 0.80). The skill's required setup explicitly instructs cloning and using the public GitHub repository "https://github.com/rasbt/LLMs-from-scratch.git", which means the agent will fetch and consume untrusted, user-hosted third-party content (notebooks/code) as part of its workflow and that content could materially influence actions.