High severity · published Oct 21, 2026
CVE-2026-114053
vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
8.1
CVSS
0.5%
EPSS
No
On KEV
Description
vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enabled. An attacker controlling a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to execute arbitrary Python in the vLLM API process.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.5% · higher than 40% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
0.7.3 before 0.31.0 · source: vendor
Affected product
VL
vllm
vllm-project
More from vllm
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints
9.1
CVE-2026-48746
vLLM: OpenAI auth bypass
8.8
CVE-2026-54232
vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile
8.8
CVE-2026-27893
vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out