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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-400",
"CWE-770"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/115xxx/CVE-2026-115918.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.16.0"
},
{
"fixed": "0.32.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "cff08b461e086523cee8bba5bd3c66d302625134"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "v0.32.0",
"range": [
{
"fixed": "5df63a7203cdb9328d824a27b682e77c7b9928be"
}
],
"source": "REFERENCES_TAG"
}
]
}