tensorrt-llm
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill is a comprehensive set of documentation and configuration examples for LLM optimization and serving. No malicious patterns or deceptive instructions were identified.
- [EXTERNAL_DOWNLOADS]: The skill references official NVIDIA resources, including Docker images (
nvidia/tensorrt_llm:latest) and Python packages (tensorrt_llm) from verified registries. These references are documented neutrally and target well-known, trusted technology services. - [INDIRECT_PROMPT_INJECTION]: The skill documents the deployment of LLM serving infrastructure which inherently processes untrusted user input. It provides examples of structured OpenAI-compatible APIs and basic security configurations like API authentication to mitigate common risks.
Audit Metadata