find-your-level

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches ROADMAP.md from GitHub (https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/ROADMAP.md), which is a repository path where external users can potentially commit content, but it is the repository's main branch file rather than unmoderated user submissions like issues/PRs.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch ROADMAP.md from https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/ROADMAP.md if the repository is not cloned locally, constituting a weak/unknown/suspicious external operational dependency.