Vulnerability Intelligence Report
vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
CVE-2026-114053
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.
No Active Exploit Signals
CVSS Base Score
9.2
CRITICAL
EPSS Probability:0.46%
Executive Threat Verdict
Evaluating...
Evaluating Threat Landscape...
Assessing known weaponization, exploitation telemetry, and federal advisories.
Attack Surface
—
Authentication
—
Weaponization
—
SSVC Action
—
Weaknesses (CWE)
CWE-94 ↗Improper Control of Generation of Code ('Code Injection')
Affected Products & Versions
| Vendor | Product | Affected Versions |
|---|---|---|
| vllm-project | vllm | 0.7.3 < 0.31.0 (affected), 0.31.0 (unaffected) |
References & Technical Advisories
No reference links found.
Threat Intelligence Signals
EPSS Score
0.462%
GitHub Advisory
Identity & Timeline
| Status | PUBLISHED |
| Assigning Authority | VulnCheck · Bug Bounty Provider · USA |
| Reserved | 2026-10-20T21:42:27 |
| Published | 2026-10-21T00:36:29 |
| Patch Date | 2026-10-06 |
| Last Updated | 2026-10-27T21:41:51 |
Community Chatter & Buzz