claude-certification
Warn
Audited by Snyk on Aug 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly falls back to fetching route, lesson, and code files at runtime from https://raw.githubusercontent.com/fancyboi999/ai-engineering-from-scratch-zh/main/, which can supply prompt-controlling data (program/lesson JSON) and executable scripts (e.g., code/main.py) that the agent may run.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata