Description
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.
Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:HWeakness enumeration
Affected software
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.16.0, < 0.32.0 |
References
- https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134Patch
- https://github.com/vllm-project/vllm/pull/50300Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cfPatch, Vendor Advisory
Timeline
- Published
- Oct 26, 2026
- Last modified
- Oct 30, 2026
- NVD status
- Analyzed