vllm-deployment

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs pulling container images and models from public registries (e.g., Docker pulls and the HuggingFace Model Hub referenced under "Configuration Reference" / "References") and running them with vLLM so the agent will load and read outputs from untrusted, user-provided models as part of its workflow, enabling potential indirect prompt injection.