vLLM
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.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS9.2critical · scored by CNA · CWE-94
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
vllm-project vllm
- >= 0.7.3, < 0.31.0
Fixed in 0.31.0
Mitigation
Upgrade vllm to 0.31.0 or later.
References
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.