vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
Published 28 Oct 2026 · Updated 29 Oct 2026
Is your project on an affected vllm?
Look after several Python apps? Indie watches up to 15 repos, private ones too, for $5 a month. See Indie
Affected package
- Affected
- >=0.16.0 <0.32.0
- Fixed in
- 0.32.0
pip install 'vllm>=0.32.0'Details
Summary
vLLM's /v1/responses endpoint accepts request-level chat_template_kwargs, but does not apply the --trust-request-chat-template gate that protects Chat Completions, render, tokenize, and pooling paths.
When the server is run with the documented default trust_request_chat_template=False and no explicit --chat-template, a Responses request can pass:
{"chat_template_kwargs": {"chat_template": "<attacker Jinja template>"}}That key is preserved by ChatParams.get_apply_chat_template_kwargs() and then bound as the chat_template parameter to the shared HF renderer. Prior vLLM advisories establish that request-controlled Jinja chat templates can cause CPU/memory exhaustion. This report covers the current-head Responses sibling path missed by the earlier fixes.
Technical Details
The shared OpenAI frontend has a validation helper that rejects request-supplied chat templates unless the trust flag is enabled. It explicitly checks both top-level chat_template and chat_template_kwargs["chat_template"].
Responses is a separate serving path:
vllm/entrypoints/openai/responses/protocol.pyexposeschat_template_kwargs.ResponsesRequest.build_chat_params()merges request kwargs.OpenAIServingResponses._effective_chat_template_kwargs()uses those kwargs.ChatParams.get_apply_chat_template_kwargs()preserves a requestchat_templatekey when the server chat template isNone.vllm/renderers/hf.pyunpacks the result intosafe_apply_chat_template.
There is no equivalent trust gate in vllm/entrypoints/openai/responses/serving.py.
Impact
An authenticated caller who can submit /v1/responses requests can supply a request-controlled Jinja chat template despite the trust flag being disabled. The expected fixed behavior is the same as Chat Completions: reject chat_template_kwargs["chat_template"] unless the server was started with --trust-request-chat-template.
Suggested Fix
- Add
trust_request_chat_templatetoOpenAIServingResponses. - Pass
args.trust_request_chat_templatewhen constructing the Responses serving object. - Reject
request.chat_template_kwargs["chat_template"]before rendering when trust is false. - Keep ordinary kwargs such as
enable_thinkingworking. - Add regression tests for default-deny and opt-in-allow behavior on
/v1/responses.
Affected Package/Versions
Source sweep found the affected shape in:
v0.16.0v0.18.0v0.20.0v0.21.0v0.22.0v0.22.1v0.23.0- current checkout
470229c37efaf69c86e8bc97482b0b1ff7551c65 - current
origin/mainb3f0a0a0df76dda92ec4b2c9335f77e84adad911
Suggested affected range:
>= 0.16.0, <= 0.23.0
Appendix: Duplicate Research
This is related to, but distinct from:
GHSA-6fvq-23cw-5628/CVE-2025-61620GHSA-69j4-grxj-j64p/CVE-2025-62426
Those advisories establish the security impact of request-controlled Jinja templates and chat_template_kwargs, but they cover older Chat Completions/tokenize implementations. This report covers a current /v1/responses sibling path that still lacks the trust gate.
Local prior submissions this report..029 do not cover this root cause.
This advisory was fixed in MR50300.
Is GHSA-x567-49g5-p4cf in any of your client repos?
Checking one package by hand is fine. Checking it across forty client projects is not. NPMscan reads the lockfiles in every GitHub repo you pick, finds each project with an affected vllm, and gives you the command that fixes it.
More advisories for vllm
- LowCVE-2026-115917vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server · 28 Oct 2026
- MediumCVE-2026-115913vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine · 28 Oct 2026
- MediumCVE-2026-115914vLLM DeepSeek-OCR image processing vulnerable to denial of service · 28 Oct 2026
- HighCVE-2026-115915vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE · 28 Oct 2026
- HighCVE-2026-115912vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled · 28 Oct 2026
- MediumCVE-2026-115916vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS) · 28 Oct 2026
References
- Linkgithub.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf
- Advisorynvd.nist.gov/vuln/detail/CVE-2026-115918
- Linkgithub.com/vllm-project/vllm/pull/50300
- Linkgithub.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134
- Packagegithub.com/vllm-project/vllm
- Linkgithub.com/vllm-project/vllm/releases/tag/v0.32.0
Advisory data from OSV.dev (opens OSV.dev in a new tab), refreshed daily.