vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
Exact source revision recorded 27 Oct 2026 22:45:55 UTC. It does not establish the source's current position. Latest evidence.
cve-program · CVE-2026-114053
PublishedvLLM 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.
- Source published
- 21 Oct 2026 00:36:29 UTC
- Source modified
- 27 Oct 2026 21:41:51 UTC
- Observed here
- 27 Oct 2026 22:45:55 UTC
- Source terms
- CVE Program Terms of Use
Original source record · Cite this exact observation · Complete original publisher JSON
This view projects the publisher's source fields for reading; the original JSON retains additional fields and CVE enrichment containers. Attribution: cve-program · CVE Program Terms of Use. Source text is retained; field grouping and change labels are provided by ChangeIntel.
CVSS 4.0 · 9.2 CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CVSS 3.1 · 8.1 CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H