MediumCVE-2026-115918

vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs (CVE-2026-115918)

Published 26.10.2026Last modified 28.10.2026Sources: OSV, Hersteller, CVE.org

What is affected, what to do

Update vllm to version 0.32.0.

Affected: vLLM gte 0.16.0, < 0.32.0..*

Not sure whether and how you are affected? Ask a question about this vulnerability

Metrics

6.5

Priority

XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

Source: Vendor (CNA), CVSS v3

6.5

CVSS v3

Severity Medium on the scale from 0 to 10.

Source: OSV, Hersteller, CVE.org

0.4 %

EPSS score

Low — model estimates < 1% exploitation likelihood.

Source: FIRST EPSS, percentile 28.6

Show all metrics

Severity: Medium
Priority (0–325) The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first? Read in glossary: 69.06 Methodology
Exploit maturity An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack. Read in glossary: no public PoC known
XIEM Effective CVSS XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command. Read in glossary: 6.5 Methodology
CVSS v3 CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions. Read in glossary: 6.5
EPSS score The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“. Read in glossary: 0.4 %; Low — model estimates < 1% exploitation likelihood.
EPSS percentile The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking. Read in glossary: 28.6; Elevated — this CVE ranks above at least 10% of all CVEs scored today.
KEV status The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching. Read in glossary: —
Published: 26.10.2026
CWE CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect. Read in glossary: CWE-400, CWE-770

Detection rules

No NEOSEC detection rule is available for this vulnerability yet.

Classification under NIS2 and CRA

Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

NIS2 NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management. Read in glossary: Handle the vulnerability in regular vulnerability handling under Art. 21(2)(e) NIS2.
CRA The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates. Read in glossary: From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
ISO/IEC 27001 ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security. Read in glossary: Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

Description

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.py exposes chat_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 request chat_template key when the server chat template is None.
vllm/renderers/hf.py unpacks the result into safe_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_template to OpenAIServingResponses.
Pass args.trust_request_chat_template when constructing the Responses serving object.
Reject request.chat_template_kwargs["chat_template"] before rendering when trust is false.
Keep ordinary kwargs such as enable_thinking working.
Add regression tests for default-deny and opt-in-allow behavior on /v1/responses.

Affected Package/Versions

Source sweep found the affected shape in:

v0.16.0
v0.18.0
v0.20.0
v0.21.0
v0.22.0
v0.22.1
v0.23.0
current checkout 470229c37efaf69c86e8bc97482b0b1ff7551c65
current origin/main b3f0a0a0df76dda92ec4b2c9335f77e84adad911

Suggested affected range:

>= 0.16.0, <= 0.23.0

Appendix: Duplicate Research

This is related to, but distinct from:

GHSA-6fvq-23cw-5628 / CVE-2025-61620
GHSA-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.

Source: OSV (Open Source Vulnerabilities), GitHub Security Advisories, NVD (NIST), cvelistv5

Affected products

The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

Affected products
		Affected versions	Fixed in
vllm-project	vllm	`≥ 0.16.0, < 0.32.0`	—
vllm	vllm	`0.16.0 – < 0.32.0`	`0.32.0`
pip	vllm	`>= 0.16.0, < 0.32.0`	`0.32.0`
pypi	vllm	`0.30.0` `0.21.0` `0.18.0` `0.22.1` `0.18.1` `0.27.0` `0.26.0` `0.19.0` `0.17.0` `0.31.0` `0.23.0` `0.20.1` `0.22.0` `0.16.0` `0.27.1` `0.28.0` `0.25.0` `0.17.1` `0.25.1` `0.19.1` `0.20.2` `0.24.0` `0.29.0` `0.20.0`	— — — — — — — — — — — — — `0.32.0` — — — — — — — — — —

Vendors and products

Weakness classes (CWE)

CWE-400Uncontrolled Resource Consumption
Class
The product does not properly control the allocation and maintenance of a limited resource.
Entry at MITRE CWE-400
CWE-770Allocation of Resources Without Limits or Throttling
Base
The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.
Entry at MITRE CWE-770

References & sources

github.comvllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d3026251…x_refsource_MISC, Patch, web, fix
github.comvllm-project/vllm/pull/50300x_refsource_MISC, Patch, web, fix
github.comvllm-project/vllm/releases/tag/v0.32.0x_refsource_MISC, Release notes, web, advisory
github.comvllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cfx_refsource_CONFIRM, Patch, Vendor advisory, web, fix
NVD (NIST)vuln/detail/CVE-2026-115918advisory
github.comvllm-project/vllmpackage

Changes to this CVE

Who changed this CVE and when: NVD (analysis, affected products, CVSS), the CVE publisher (CNA) and additional providers such as CISA (ADP).

28.10.2026Initial analysis by NVDNVD

Newly listed as affected:

vLLM (0.16.0 – before 0.32.0)

New references:

Show 5 original changes

Individual changes of this event as published by NVD
Type	Action	Before	After
Product configuration	added	—	OR cpe:2.3:a:vllm:vllm::::::::* versions from (including) 0.16.0 up to (excluding) 0.32.0
Reference type	added	—	GitHub, Inc.: https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134 Types: Patch
Reference type	added	—	GitHub, Inc.: https://github.com/vllm-project/vllm/pull/50300 Types: Patch
Reference type	added	—	GitHub, Inc.: https://github.com/vllm-project/vllm/releases/tag/v0.32.0 Types: Release Notes
Reference type	added	—	GitHub, Inc.: https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf Types: Patch, Vendor Advisory

Source identifier: nvd@nist.gov

26.10.2026ReceivedGitHub

CVSS V3.1: AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

Weakness type: CWE-400, CWE-770

Description added or changed

New references:

Show 9 original changes

Individual changes of this event as published by NVD
Type	Action	Before	After
Description	added	—	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.
CVSS	added	—	AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weakness type (CWE)	added	—	CWE-400
Weakness type (CWE)	added	—	CWE-770
Affected versions (publisher)	added	—	New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/115xxx/CVE-2026-115918.json">CVE-2026-115918</a>
Reference	added	—	https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d302625134
Reference	added	—	https://github.com/vllm-project/vllm/pull/50300
Reference	added	—	https://github.com/vllm-project/vllm/releases/tag/v0.32.0
Reference	added	—	https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cf

Source identifier: security-advisories@github.com

Embed badge

Show the severity and KEV status of this vulnerability on your site – with a link back here. The image is updated hourly.

<a href="https://intel.neosec.eu/en/cve/CVE-2026-115918"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-115918.svg?lang=en" alt="CVE-2026-115918 – NEOSEC Intel" height="20"></a>