Skip to main content

CVE-2026-114054: Improper Access Control in vllm-project vllm

0
High
VulnerabilityCVE-2026-114054cvecve-2026-114054
Published: 10/21/2026 (10/21/2026, 00:36:30 UTC)
Source: CVE Database V5
Vendor/Project: vllm-project
Product: vllm

Description

vLLM versions before 0.31.0 have an improper access control vulnerability involving cache aliasing. Authenticated attackers can manipulate shared cache keys by supplying controlled values like EXIF ImageID or cache_salt. This allows attackers to access cached processed media from other requests or reuse key-value state, potentially leading to unauthorized data access.

CVSS v4.0

Score 7.1high

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
Low
User Interaction
None
Vuln. Confidentiality
None
Vuln. Integrity
None
Vuln. Availability
High
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:H/SC:N/SI:N/SA:N

Affected software

vllm-project

vllm

Affected versions
>=0 <0.31.0

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 10/21/2026, 01:34:12 UTC

Technical Analysis

CVE-2026-114054 describes a cache aliasing vulnerability in vLLM prior to version 0.31.0. The flaw allows authenticated attackers to collide shared cache keys by providing caller-controlled inputs such as EXIF ImageID or cache_salt. By setting a UUID EXIF ImageID, an attacker can receive cached processed media from another request. Similarly, matching cache_salt to a LoRA name enables reuse of the first-block key-value state. This improper access control issue can lead to unauthorized data exposure within the caching mechanism.

Potential Impact

The vulnerability enables authenticated attackers to access cached data belonging to other users or requests by exploiting cache key collisions. This can result in unauthorized disclosure of processed media or internal key-value state data. The CVSS 4.0 score of 7.1 indicates a high severity impact with network attack vector, low attack complexity, no user interaction, and high impact on data confidentiality.

Mitigation Recommendations

A fix is available in vLLM version 0.31.0 and later. Users should upgrade to version 0.31.0 or above to remediate this vulnerability. No additional mitigation steps are indicated in the provided data.

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
VulnCheck
Date Reserved
2026-10-20T21:42:27.669Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6ad80c012cdf04f6568caa19

Added to database: 10/21/2026, 00:49:05 UTC

Last enriched: 10/21/2026, 01:34:12 UTC

Last updated: 10/21/2026, 01:34:12 UTC

Views: 2

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