CVE-20XX-?
agent?

Vllm CVEs.

Published CVEs affecting Vllm, ranked by exploit odds.

1 CVEs · updated 2026-11-19 05:10 UTC

Reset all
  1. CVE-2026-115917

    vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with allowed_origins set to a wildcard by default. A malicious web page can use a victim's browser to reach an unauthenticated vLLM server on localhost, an internal network, or a VPN, call endpoints including GET /v1/models and POST /v1/chat/completions, consume GPU resources, and read responses. Cookie-based cross-site request forgery does not apply because credentials are disabled by default, and deployments requiring bearer authentication are exposed only when the caller already has a usable token. This issue is fixed in version 0.32.0.

    Other Browser & mail Vllm

    3.4 LOW 0.2% exploit odds Fix listed

All CVEs affecting Vllm that appear in CVE.org and NVD, sorted by how likely they are to be exploited (EPSS), with fix status and timeline.