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.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134 Patch
- https://github.com/vllm-project/vllm/pull/50300 Patch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf Patch, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 6
- Cpes+1 CPE criteria (now 1)NVD modified 2026-10-28 15:35
- StatusPublished → AnalyzedNVD modified 2026-10-28 15:35
- StatusAwaiting Analysis → PublishedNVD modified 2026-10-26 17:21
- StatusPublished → Awaiting AnalysisNVD modified 2026-10-26 18:34
- StatusReceived → PublishedNVD modified 2026-10-26 17:21
- First seenCVSS 6.5NVD modified 2026-10-26 18:17
Affected (CPE criteria) 1
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
References 4
- https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134 Patch
- https://github.com/vllm-project/vllm/pull/50300 Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf Patch, Vendor Advisory