All vulnerabilities

Servers and applications

CVE-2026-115918

Responses API bypasses trust_request_chat_template for chat_template_kwargs

Severity
Medium 6.5
Published
20 Oct 2026
Last changed
30 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.32.0
Also known as
GHSA-x567-49g5-p4cf
Sources
NVD, CVE Program, Project advisories (GitHub)

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…

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • From 0.16.0 before 0.32.0
vLLMServers and applications · cpe:a:vllm:vllm
  • From 0.16.0 before 0.32.0
vLLMServers and applications · github:vllm-project/vllm
  • From 0.16.0 before 0.32.0

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-115918
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-115918
  • GitHub Advisory Database https://github.com/advisories/GHSA-x567-49g5-p4cf
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf