CVE-2026-115917

Summary

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.

Impact & exploitability

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N

Affected products we track (1)

Recommendation

Apply the vendor fix in your normal patch cycle. Open any affected product above for its exact safe version.

Official patch: https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa ↗

Additional information

• NVD record
• https://github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aaPatch
• https://github.com/vllm-project/vllm/pull/61009Patch
• https://github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmhPatch
• https://github.com/vllm-project/vllm/releases/tag/v0.32.0