{"id":"CVE-2026-115918","published":"2026-10-26T18:17:39.440","lastModified":"2026-10-26T18:34:17.050","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.","cvssScore":6.5,"cvssSeverity":"MEDIUM","cvssVector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","cwes":["CWE-400","CWE-770"],"vendors":[],"products":[],"references":[{"url":"https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134","tags":[]},{"url":"https://github.com/vllm-project/vllm/pull/50300","tags":[]},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.32.0","tags":[]},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf","tags":[]}],"exploitRefs":[{"url":"https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134","tags":[]},{"url":"https://github.com/vllm-project/vllm/pull/50300","tags":[]},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.32.0","tags":[]},{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf","tags":[]}],"hasPoc":true,"ai":null}