CVE-2026-114053
8.1 HIGHpublic exploit availablePublished 2026-10-21 · Updated 2026-10-22
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD 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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Weaknesses
CWE-94
Public exploit & PoC references
All references
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- CRITICALCVE-2021-48016PoC
- CRITICALCVE-2024-31026
- HIGHCVE-2024-42002PoC
- LOWCVE-2024-4412PoC
- UNSCOREDCVE-2025-30045
- UNSCOREDCVE-2025-30050
- HIGHCVE-2026-0322
- MEDIUMCVE-2026-100152
Related by shared AI tags and CWE weakness class. Browse the full archive.