vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
CVSS score
9.2
EPSS probability
—
Risk score
0.9
Published
4 h ago
Etkilenen ürün ve sürüm için yayımlanan güvenlik güncellemesini uygulayın.
Impact on My Inventory
Only the personal products you have added to your account are assessed; an organisation's inventory does not appear here.
Checking session…
Vulnerability description
DayBreach AI Explanation
Verified against sourcesSources read
2
Source agreement
0/2
Evidence confidence
%37
Short explanation
vLLM versions from 0.7.3 up to but not including 0.31.0 forward the client‑supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained; when trust_remote_code is enabled, an attacker controlling a model repository revision can send a multimodal request to the unauthenticated /tokenize endpoint and execute arbitrary Python in the vLLM API process.
An unauthenticated attacker can achieve remote code execution on the vLLM server and potentially take over the service.
What should be done?
- Apply the patch commit or upgrade to vLLM 0.31.0 or later
- Enable trust_remote_code only when necessary
- Validate revisions in the model repository
- Monitor requests to the /tokenize endpoint
- Implement additional security monitoring and response measures
3 alanda kaynak uyuşmazlığı var. DayBreach bu değerleri saklamadı; kaynak karşılaştırması aşağıda gösteriliyor.
Chain of evidence and sources
vLLM 0.7.3 < 0.31.0 sürümleri, trust_remote_code etkin olduğunda /tokenize uç noktasına gönderilen mm_processor_kwargs.code_revision parametresi aracılığıyla uzaktan kod yürütme sağlar.
Bu açık için bir yama mevcut; vLLM 0.31.0 sürümüne yükseltmek veya ilgili commit’i uygulamak sorunu giderir.
CVSS puanı (9.2 vs 8.1) ve şiddet (CRITICAL vs HIGH) kaynaklar arasında çelişiyor, bu da risk değerlendirmesinde belirsizlik yaratıyor.
Show the technical text from the sources
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:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
CWE: CWE-94
This explanation was compiled automatically from the source records. Scores, active exploitation, patch and exploit status come straight from the sources.
IMPACT: Affected Products and Software
Affected Products
The following products are affected by CVE-2026-114053 vulnerability. Where our threat engine knows the exact affected versions, they are listed below.
| ID | VENDOR | PRODUCT | ACTION |
|---|---|---|---|
| 1 | vllm-project | vllm | View |
RED HAT CSAF/VEX: Product Impact Check
SCORING: CVSS from Multiple Sources
CVSS Scores
The Common Vulnerability Scoring System is a standardised framework for assessing the severity of vulnerabilities in software and systems. We collect and display CVSS scores from several sources for each CVE.
| SCORE | VERSION | SEVERITY | VECTOR | SOURCE |
|---|---|---|---|---|
| 9.2 | CVSS V4_0 | CRITICAL | 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 | CVE CNA |
| 9.2 | CVSS V40 | CRITICAL | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X | NVD |
| 8.1 | CVSS V3_1 | HIGH | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | CVE CNA |
| 8.1 | CVSS V31 | HIGH | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | NVD |
Patch and Remediation Guide
Solution & Remediation Advisory
2 doğrulanmış yama veya düzeltilmiş sürüm kanıtı bulundu.
Public exploit and active exploitation status
Verified exploit intelligence
No verified public PoC, exploit repository or Metasploit module has been found for this CVE yet.
Weakness Classification and Attack Patterns (CWE & CAPEC)
CWE - Common Weakness Enumeration
While CVE identifies specific instances of vulnerabilities, CWE categorises the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-114053 is associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-114053 weaknesses.
Attack Vector and Accessibility
Official Sources and Advisories
CVSS Vector Radar Chart
9.2 / 10Vulnerability Scoring Details
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:NYama doğrulandı
Weakness Type (CWE & CAPEC)
Similar Vulnerabilities
Get this vulnerability through the API
Affected products, version ranges, exploitation status and patch information in a single request, with a free key.
curl -H "x-api-key: $DAYBREACH_API_KEY" \ "https://api.daybreach.dev/api/v1/intel/cves/CVE-2026-114053"