cveboard RSS feed

CVE-2026-114053

CVE.org · Published

Historical CVEsJSONAI instructions

Record status
Published
Identifier year (not publication year)
2026
Source publication
Source updated
Imported by cveboard
Source snapshot
cve_2026-10-24_midnight_baseline ·

Plain text

CNA source text (English)

vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision

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.

Scoped product and version facts

Fix information unknown; no fixed version is derived here. Missing information does not prove that no fix exists.

Exploitation unknown; this catalogue does not assess exploitation.

vllm

Vendor
vllm-project
Product
vllm
Platforms
Unknown
Default status
unaffected
vllm · Scoped product and version facts
Version (version)Status (status)Version scheme (versionType)Exclusive end (lessThan)Inclusive end (lessThanOrEqual)Status changes (at → status)
0.7.3affectedsemver0.31.0UnavailableNone listed
0.31.0unaffectedsemverUnavailableUnavailableNone listed