CVE-2026-114053
CRITICAL
INFO
Priority: 0.04
BB Relevance:
78/100
Published: 2026-10-21
Modified: 2026-10-27
First seen: 2026-10-29
Status: active
Attack Surface
Network
Low Complexity
No Auth
No Interaction
Conf. Impact
Integ. Impact
CVSS Vector Breakdown
AV:
Network
AC:
Low
PR:
None
UI:
None
S:
X
AT:
Present
VC:
High
VI:
High
VA:
High
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.