Skip to main content

CVE-2026-90878: Resource Consumption in vllm-project vLLM

0
Medium
VulnerabilityCVE-2026-90878cvecve-2026-90878
Published: 09/15/2026 (09/15/2026, 04:15:11 UTC)
Source: CVE Database V5
Vendor/Project: vllm-project
Product: vLLM

Description

CVE-2026-90878 is a medium severity vulnerability in vllm-project vLLM versions 0.27.0 and 0.27.1. It involves resource consumption caused by manipulation of the chat_template argument in the Jinja Template Rendering component at the /v1/chat/completions endpoint. The vulnerability can be exploited remotely without user interaction and requires low privileges. A fix has been proposed but is not yet accepted.

CVSS v4.0

Score 5.3medium

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
Low
User Interaction
None
Vuln. Confidentiality
None
Vuln. Integrity
None
Vuln. Availability
Low
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P

Affected software

vllm-project

vLLM

Affected versions
=0.27.0=0.27.1
vllm
pkg:pypi/vllm
Affected versions
=0.27.0=0.27.1
CPE configurations
cpe:2.3:a:vllm-project:vllm:*:*:*:*:*:*:*:*

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/15/2026, 04:46:27 UTC

Technical Analysis

This vulnerability affects vllm-project vLLM up to version 0.27.1 in the Jinja Template Rendering component of the /v1/chat/completions endpoint. An attacker can remotely manipulate the chat_template argument to cause resource consumption, potentially leading to denial of service or degraded performance. The vulnerability has been publicly disclosed, and a pull request to fix it is pending acceptance, indicating no official patch is available yet.

Potential Impact

Exploitation of this vulnerability can lead to resource exhaustion on the affected system, potentially causing denial of service or degraded service availability. The attack requires low privileges and no user interaction, increasing the risk of remote exploitation. However, there are no known exploits in the wild at this time.

Mitigation Recommendations

A fix is not yet officially available as the pull request to address the issue awaits acceptance. Users should monitor the vendor's repository or advisory channels for the official patch and apply it promptly once released. Until then, consider implementing resource usage limits or other protective controls at the application or infrastructure level to mitigate potential impact.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulDB
Date Reserved
2026-09-14T07:16:13.062Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6aa8ca4255bf5e2cf521ce78

Added to database: 09/15/2026, 04:32:02 UTC

Last enriched: 09/15/2026, 04:46:27 UTC

Last updated: 09/15/2026, 05:16:57 UTC

Views: 6

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses