andrew-ng
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a philosophical and instructional persona based on Andrew Ng's principles (e.g., 'Task-Based Automation', 'Agentic Workflows'). The instructions focus on rapid prototyping and data-centric AI.
- [SAFE]: All external references and URLs point to reputable, well-known domains such as Stanford University, Coursera, DeepLearning.AI, and official social media profiles. No typosquatting or malicious redirects were identified.
- [SAFE]: There are no detected obfuscation techniques (Base64, zero-width characters, or homoglyphs) in the instruction set or reference files.
- [SAFE]: The skill does not include any commands for remote code execution, unauthorized file system access, or network exfiltration. The heuristic mentioning 'insecure code' is explicitly scoped to 'local prototypes' for development speed and does not instruct the agent to bypass security constraints in a production context.
Audit Metadata