CVE-2026-115918

vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

Published Oct 26, 2026 CVSS 3.1 · 6.5 Medium EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

vLLM, an inference and serving engine for large language models, contains a flaw in the /v1/responses endpoint that allows an authenticated caller to supply a malicious template through chat_template_kwargs[chat_template] when no server template is configured. The application fails to enforce the trust_request_chat_template policy, enabling the attacker‑controlled template to be rendered by Jinja. This is a resource exhaustion vulnerability (CWE-400) involving excessive allocation (CWE-770) that can lead to uncontrolled CPU or memory consumption, effectively causing a denial of service on the host running the vLLM service. Additionally, the lack of template trust enforcement may permit arbitrary Jinja code execution, classified as CWE-94.

Affected Systems

vLLM engines with versions between 0.16.0 and 0.31.x deployed by organizations that rely on the /v1/responses API. The affected product is provided by the vllm-project under the vllm namespace.

Risk and Exploitability

The CVSS score of 6.5 indicates moderate severity. No EPSS data is available, so the current exploitation probability cannot be quantified, and the vulnerability is not listed in the CISA KEV catalog. Because the exploit requires an authenticated request to the /v1/responses endpoint, an attacker must first obtain valid credentials or access token. Once authenticated, the attacker can supply the malicious template, potentially exhausting server resources. The absence of a restriction on trusted templates means that the attack can be performed by any authenticated user who has permission to use the endpoint, and the uncontrolled template rendering also creates a risk of arbitrary code execution (CWE-94).

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade the vLLM installation to version 0.32.0 or newer where the template bypass is fixed.
  • If an upgrade is delayed, limit the /v1/responses endpoint to trusted users only and disable Jinja rendering for externally supplied chat templates.
  • Continuously monitor CPU and memory utilisation of the vLLM service to detect abnormal spikes that may indicate exploitation.

Generated by OpenCVE AI on October 27, 2026 at 13:26 UTC.

Tracking

Sign in to view the affected projects.

Advisories

Source ID Title
Github GHSA Github GHSA GHSA-x567-49g5-p4cf vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
CPEs cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*
Type Values Removed Values Added
First Time appeared Vllm
Vllm vllm
Vllm-project
Vllm-project vllm
Vendors & Products Vllm
Vllm vllm
Vllm-project
Vllm-project vllm
Type Values Removed Values Added
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.
Title vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
Weaknesses CWE-400
CWE-770
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'}

Weaknesses
  • CWE-400

    Uncontrolled Resource Consumption

  • CWE-770

    Allocation of Resources Without Limits or Throttling

  • CWE-94

    Improper Control of Generation of Code ('Code Injection')

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Oct 30, 2026, 2:22 PM
Reserved
Oct 23, 2026, 8:21 PM
Status
Analyzed
Published
Oct 26, 2026, 6:17 PM
Modified
Oct 30, 2026, 3:16 PM
Severity
Moderate
Public date
Oct 26, 2026, 5:21 PM