nemo-guardrails
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains strings typically associated with prompt injection, such as "Ignore previous instructions" and "Pretend you are DAN". However, these are exclusively used within code examples to demonstrate how the NeMo Guardrails framework identifies and blocks such attacks. They do not represent an attempt to override the AI agent's behavior.
- [EXTERNAL_DOWNLOADS]: The documentation instructs the user to install the 'nemoguardrails' package via pip. This is the official Python package for NVIDIA's open-source safety framework and is considered a safe and standard dependency for this use case.
- [SAFE]: All referenced URLs point to official NVIDIA documentation or their verified GitHub repository (NVIDIA/NeMo-Guardrails). The skill operates purely as an instructional resource without any malicious code or hidden behaviors.
Audit Metadata