tensorrt-llm

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill references standard installation methods for the tensorrt-llm and torch libraries via PyPI and Docker Hub. These are official distribution channels for the specified software.
  • [PROMPT_INJECTION] (SAFE): The skill is designed to process user prompts for LLM inference. While this creates a surface for indirect prompt injection, the risk is mitigated as the skill operates within a restricted execution environment without access to sensitive system resources or arbitrary command execution.
  • [COMMAND_EXECUTION] (SAFE): CLI commands such as trtllm-serve are used for their intended purpose of serving models and do not involve unsanitized user input in the command-line construction.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:19 PM