CVE-2026-25960 SSRF Protection Bypass in vLLM

vLLM is an inference and serving engine for large language models LLMs. The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the loadfromurlasync method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. The SSRF fix uses...

CVE-2026-25960

vLLM is an inference and serving engine for large language models LLMs. The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the loadfromurlasync method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. The SSRF fix uses...

GHSA-V359-JJ2V-J536 vLLM has SSRF Protection Bypass

Summary The SSRF protection fix for https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc can be bypassed in the loadfromurlasync method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. Affected Component - File:...

EUVD-2026-10356

vLLM has SSRF Protection Bypass...

vLLM has SSRF Protection Bypass

Summary The SSRF protection fix for https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc can be bypassed in the loadfromurlasync method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. Affected Component - File:...

ado-vllm-performance (>=1.2.2 <=1.3.3), agentclinic (=0.1.0) +73 more potentially affected by CVE-2026-25048 via xgrammar (>=0.1.11 <=0.1.29)

xgrammar PYPI version =0.1.11, =1.2.2, =0.0.0, =2.3.5, =0.8.4, =0.2.2, =0.2.0, =0.1.0, =1.0.1rc1, =0.0.2, =0.1.1, =0.1.1, =0.0.2, =0.1.0 and more Source cves: CVE-2026-25048 Source advisory: OSV:GHSA-7RGV-GQHR-FXG3...

CVE-2026-27482 vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow...

GHSA-Q5FH-2HC8-F6RQ vulnerabilities

Vulnerabilities for packages: tritonserver-backend-vllm-cuda-12.9, py3-vllm-cuda-12.4, airflow...

Malicious code in vllm-plugins (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: kam193 4fa0706d497278a502d158c89d51645a6f4e8187ca325aacaa59facccf542a03 Generic campaign for all likely research / pentests, where the amount or art of collected data raises questions about the privacy, security and ethical side. -...

Server-Side Request Forgery (SSRF)

vllm is vulnerable to a Server-Side Request Forgery SSRF. The vulnerability is due to inconsistent URL parsing and hostname validation in the MediaConnector class when processing user-supplied media URLs, which allows an attacker to bypass host restrictions and coerce the vLLM server into making...

CVE-2026-22778

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. A remote attacker can exploit this vulnerability by sending a specially crafted video URL to vLLM's multimodal endpoint. This action causes vLLM to leak a heap memory address, significantly reducing the...

CVE-2026-22778

vLLM is an inference and serving engine for large language models LLMs. From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guess...

CVE-2026-22778 vLLM leaks a heap address when PIL throws an error

vLLM is an inference and serving engine for large language models LLMs. From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guess...

CVE-2026-22778

vLLM is an inference and serving engine for large language models LLMs. From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guess...

CVE-2026-22778 vLLM leaks a heap address when PIL throws an error

vLLM is an inference and serving engine for large language models LLMs. From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guess...

Exploit for Code Injection in Vllm

No d...

GHSA-QH4C-XF7M-GXFC vLLM vulnerable to Server-Side Request Forgery (SSRF) through MediaConnector

Summary A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods obtain and process media from URLs provided by users, using different Python parsing libraries when restrictin...

ado-vllm-performance (>=1.2.2 <=1.3.3), agentclinic (=0.1.0) +31 more potentially affected by CVE-2026-24779 +1 more via vllm (>=0.10.0 <=0.14.0)

vllm PYPI version =0.10.0, =1.2.2, =0.0.0, =2.3.5, =0.2.0, =0.1.0, =1.0.1rc1, =0.0.4, =0.1.0, =0.3.9, =0.5.2, =0.1.0, =0.1.5, =0.2.0 - gfmrag =2.0.0 and more Source cves: CVE-2026-24779, CVE-2026-25960 Source advisory: OSV:GHSA-QH4C-XF7M-GXFC...

CVE-2026-24779

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class, specifically within the loadfromurl and loadfromurlasync methods. An attacker can exploit differing interpretations of...

ado-vllm-performance (>=1.2.2 <=1.3.3), agentclinic (=0.1.0) +31 more potentially affected by CVE-2026-24779 via vllm (>=0.10.0 <=0.14.0)

vllm PYPI version =0.10.0, =1.2.2, =0.0.0, =2.3.5, =0.2.0, =0.1.0, =1.0.1rc1, =0.0.4, =0.1.0, =0.3.9, =0.5.2, =0.1.0, =0.1.5, =0.2.0 - gfmrag =2.0.0 and more Source cves: CVE-2026-24779 Source advisory: SNYK:PYTHON-VLLM-15123970...