Lucene search
+L

126 matches found

NVD
NVD
•added 2026/11/13 10:17 a.m.•9 views

CVE-2026-126395

vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitizemessage whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak...

6.9CVSS0.00346EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/11/13 9:35 a.m.•30 views

CVE-2026-126395 vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()

vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitizemessage whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak...

6.9CVSS0.00346EPSS
SaveExploits0References2
CVE
CVE
•added 2026/11/13 9:35 a.m.•14 views

CVE-2026-126395

The vLLM library (versions 0.14.0rc1 before 0.31.0) is vulnerable to a heap address disclosure in the sanitize_message() function. The root cause is a lowercase-only regex that fails to scrub uppercase PIL image addresses. Unauthenticated attackers can exploit this by sending a crafted PNG to end...

6.9CVSS5.8AI score0.00346EPSS
SaveExploits0References2
osv_cve
osv_cve
•added 2026/11/13 9:35 a.m.•9 views

CVE-2026-126395 vLLM 0.14.0rc1 before 0.31.0 Heap Address Disclosure via sanitize_message()

vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitizemessage whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak...

6.9CVSS5.8AI score
SaveExploits0References4
EUVD
EUVD
•added 2026/11/13 9:35 a.m.•11 views

EUVD-2026-125170

vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitizemessage whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak...

6.9CVSS5.8AI score0.00346EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/10/27 3:36 p.m.•58 views

EUVD-2026-107004

vLLM: Request-controlled mmprocessorkwargs.coderevision allows remote code execution...

9.2CVSS8AI score0.00462EPSS
SaveExploits0References7
RedhatCVE
RedhatCVE
•added 2026/10/21 5:52 p.m.•18 views

CVE-2026-114052

A flaw was found in vLLM. This vulnerability allows an unauthenticated remote attacker to cause a Denial of Service DoS via memory exhaustion. When serving MOSS-Audio models, the unauthenticated tokenize endpoint caches processor configurations in an unbounded cache. By submitting requests with...

8.7CVSS7.5AI score0.00506EPSS
SaveExploits0References5
osv_ghsa
osv_ghsa
•added 2026/10/21 3:32 a.m.•16 views

GHSA-F623-HJM8-5WG5 Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-h3rc-6mm3-gc2m. This link is maintained to preserve external references. Original Description vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mmprocessorkwargs.coderevision to Transformers...

9.2CVSS7.9AI score0.00462EPSS
SaveExploits0References4
Github Security Blog
Github Security Blog
•added 2026/10/21 3:32 a.m.•27 views

Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-h3rc-6mm3-gc2m. This link is maintained to preserve external references. Original Description vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mmprocessorkwargs.coderevision to Transformers...

9.2CVSS7.9AI score0.00462EPSS
SaveExploits0References5Affected Software1
Snyk
Snyk
•added 2026/10/21 3:00 a.m.•29 views

Arbitrary Code Injection

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Arbitrary Code Injection via the /tokenize API endpoint, which does not enforce authentication even when the --api-key option is configured. An...

9.2CVSS7.4AI score0.00462EPSS
SaveExploits0References2
Snyk
Snyk
•added 2026/10/21 3:00 a.m.•26 views

Allocation of Resources Without Limits or Throttling

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling via MossAudioProcessingInfo.gethfprocessor in MOSS-Audio model serving, which caches a...

8.7CVSS7.4AI score0.00506EPSS
SaveExploits0References2
NVD
NVD
•added 2026/10/21 1:17 a.m.•43 views

CVE-2026-114053

vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when trustremotecode is enabled. An attacker controlling a revision in the...

9.2CVSS0.00462EPSS
SaveExploits0References3
osv_pysec
osv_pysec
•added 2026/10/21 1:17 a.m.•19 views

PYSEC-2026-4361

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mmprocessorkwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized melconfig values to...

8.7CVSS7.5AI score0.00506EPSS
SaveExploits0References2
PyPA
PyPA
•added 2026/10/21 1:17 a.m.•12 views

PYSEC-2026-4361

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mmprocessorkwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized melconfig values to...

8.7CVSS7.5AI score0.00506EPSS
SaveExploits0References2Affected Software1
NVD
NVD
•added 2026/10/21 1:17 a.m.•19 views

CVE-2026-114052

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mmprocessorkwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized melconfig values to...

8.7CVSS0.00506EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/10/21 12:36 a.m.•14 views

CVE-2026-114052 vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mmprocessorkwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized melconfig values to...

8.7CVSS7.5AI score0.00506EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/10/21 12:36 a.m.•46 views

CVE-2026-114053 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 mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when trustremotecode is enabled. An attacker controlling a revision in the...

9.2CVSS0.00462EPSS
SaveExploits0References3
Mend
Mend
•added 2026/10/21 12:36 a.m.•66 views

CVE-2026-114053

vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when trustremotecode is enabled. An attacker controlling a revision in the...

9.2CVSS8AI score0.00462EPSS
SaveExploits0References3
CVE
CVE
•added 2026/10/21 12:36 a.m.•105 views

CVE-2026-114053

The vLLM library versions 0.7.3 before 0.31.0 is vulnerable to Remote Code Execution (RCE) via the mm_processor_kwargs.code_revision parameter. The application forwards this user-supplied revision to Transformers AutoProcessor.from_pretrained . If trust_remote_code is enabled, an attacker who con...

9.2CVSS8AI score0.00462EPSS
SaveExploits0References3Affected Software1
osv_cve
osv_cve
•added 2026/10/21 12:36 a.m.•29 views

CVE-2026-114053 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 mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when trustremotecode is enabled. An attacker controlling a revision in the...

9.2CVSS6.7AI score
SaveExploits0References5
Rows per page
Query Builder