tensorrt-llm

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's serving instructions explicitly state trtllm-serve performs "automatic model download and compilation" (SKILL.md and references/serving.md) and points to public model hubs like HuggingFace, meaning it fetches and runs untrusted, user-hosted models whose outputs can directly influence generation and downstream actions.