tensorrt-llm
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates model optimization and deployment using official NVIDIA tools and libraries. It instructs users to obtain dependencies from verified sources such as PyPI and NVIDIA's official Docker registry.
- [SAFE]: All network activity described is restricted to local API communication and interaction with well-known, trusted domains for model weights and documentation (HuggingFace, GitHub).
- [SAFE]: No malicious patterns such as prompt injection, credential harvesting, or obfuscated execution paths were identified in the skill's instructions or referenced documentation.
Audit Metadata