guardrails-developer-guide
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from NVIDIA's official domain (docs.nvidia.com). This is a well-known and trusted source for product documentation.- [SAFE]: The skill includes explicit security instructions to never ask for real API keys or tokens, utilizing placeholders and recommending secure local storage for secrets.- [INDIRECT_PROMPT_INJECTION]: The skill ingests external documentation as context. While this represents a surface for indirect prompt injection, the risk is mitigated by sourcing content exclusively from the vendor's official documentation.
Audit Metadata