vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

[ Description ]Official 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.

[ Fixes ]Fixes and patches

• vllm 0.32.0Fixed version · GitHub Advisories · pip package vllm: upgrade to 0.32.0 or later (affected >= 0.16.0, < 0.32.0)
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD
• Patch on github.comVendor patch or bulletin · NVD · Reference tagged 'Patch' by NVD

[ Advisories ]Government CERT advisories

• BSI CERT-Bund19 Oct 2026WID-SEC-2026-4051

  vllm: Multiple vulnerabilities Translated from German

  CVE-2026-115918CVE-2026-115911CVE-2026-115912+6 more CVEs

[ Packages ]Affected open-source packages

• vllm pipAffected >= 0.16.0, < 0.32.0 · fixed in 0.32.0 · GHSA-x567-49g5-p4cf

[ References ]References

• github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134Patch
• github.com/vllm-project/vllm/pull/50300Patch
• github.com/vllm-project/vllm/releases/tag/v0.32.0Release Notes
• github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cfPatchVendor Advisory