CVE-2026-47155

What it is

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.

At a glance

Exploitability

Can be exploited over the network without logging in. High risk of data tampering.

Exploit odds

0.2% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-06-22 23:16 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-10-25 23:10 UTC Last updatedMost recent change to the record

Details

Published

2026-06-22 23:16 UTC

Last modified

2026-10-25 23:10 UTC

Exploit probability

0.2% · EPSS, next 30 days

Weakness

CWE-345

Record status

Analyzed

Affected

• Vllm < 0.22.0

Attack profile CVSS 3.1 · 6.5

Attack vector

Network

Complexity

High

Privileges needed

None

User interaction

None

Scope

Unchanged

Confidentiality

Low

Integrity

High

Availability

None