find-your-level

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads an external remote file (ROADMAP.md from raw.githubusercontent.com) which, while hosted on a trusted platform, represents external repository content that could contain arbitrary text injected by contributors.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch a remote ROADMAP.md from an arbitrary GitHub repository (fancyboi999/ai-engineering-from-scratch-zh) during runtime when not cloned locally, presenting an unverified external third-party dependency.