CVE-2026-115918

Summary

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat_template_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.

Impact & exploitability

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

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/cff08b461e086523cee8bba5bd3c66d302625134 ↗

Additional information

• NVD record
• https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134Patch
• https://github.com/vllm-project/vllm/pull/50300Patch
• https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cfPatch
• https://github.com/vllm-project/vllm/releases/tag/v0.32.0