Lucene search
+L

19 matches found

EUVD
EUVD
•added 2026/10/28 9:14 p.m.•28 views

EUVD-2026-110039

vLLM: Responses API bypasses trustrequestchattemplate for chattemplatekwargs...

6.5CVSS6.1AI score0.0035EPSS
SaveExploits0References5
SUSE CVE
SUSE CVE
•added 2026/10/28 12:46 a.m.•20 views

SUSE CVE-2026-115918

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References3
NVD
NVD
•added 2026/10/26 6:17 p.m.•23 views

CVE-2026-115918

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS0.0035EPSS
SaveExploits0References4
osv_pysec
osv_pysec
•added 2026/10/26 6:17 p.m.•21 views

PYSEC-2026-4349

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References4
PyPA
PyPA
•added 2026/10/26 6:17 p.m.•17 views

PYSEC-2026-4349

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References4Affected Software1
Vulnrichment
Vulnrichment
•added 2026/10/26 5:21 p.m.•13 views

CVE-2026-115918 vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/26 5:21 p.m.•27 views

CVE-2026-115918 vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References6
Cvelist
Cvelist
•added 2026/10/26 5:21 p.m.•41 views

CVE-2026-115918 vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

6.5CVSS0.0035EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/26 5:21 p.m.•48 views

CVE-2026-115918

The vLLM inference and serving engine (versions 0.16.0 through 0.32.0 ) contains a vulnerability in the /v1/responses endpoint. An authenticated caller can provide an attacker-controlled template via chat_template_kwargs[chat_template] when no server template is configured. Because ChatParams.get...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References4Affected Software1
Mend
Mend
•added 2026/10/26 5:21 p.m.•19 views

CVE-2026-115918

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chattemplatekwargschattemplate when no server template is configured...

7.1CVSS6AI score0.0035EPSS
SaveExploits0References6
Positive Technologies
Positive Technologies
•added 2026/10/26 12:00 a.m.•16 views

PT-2026-125028

Name of the Vulnerable Software and Affected Versions vLLM versions 0.16.0 through 0.31.0 Description The '/v1/responses' endpoint allows an authenticated user to provide a malicious template via the chat template variable within chat template kwargs when no server template is configured. The get...

6.5CVSS6AI score0.0035EPSS
SaveExploits0References9
Positive Technologies
Positive Technologies
•added 2026/10/26 12:00 a.m.•11 views

PT-2026-132752

vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to place an attacker-controlled template in chat template kwargschat template when no server template is configured. ChatParams.get apply chat...

6.5CVSS6AI score
SaveExploits0References5
Snyk
Snyk
•added 2026/09/15 5:14 a.m.•19 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 in the Jinja Template Rendering of the /v1/chat/completions endpoint when manipulating the...

5.3CVSS5.3AI score0.00533EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/06/29 12:00 a.m.•51 views

PT-2026-53452

Summary The environment variables KERNEL XXX used during the rendering of the Kubernetes manifest are vulnerable to Server Side Template Injection SSTI. By including Jinja2 template expressions it is possible to execution Python code and OS Commands in the Enterprise Gateway service. The code can...

10CVSS6.3AI score0.00767EPSS
SaveExploits1References6
CNNVD
CNNVD
•added 2026/04/06 12:00 a.m.•33 views

BentoML security vulnerabilities

BentoML is an open-source model service library developed by BentoML. It is used to build high-performance and scalable artificial intelligence applications using Python. Versions of BentoML prior to 1.4.38 contained a security vulnerability. This vulnerability stemmed from the Dockerfile...

9.6CVSS6.3AI score0.00398EPSS
SaveExploits1References2
Vulnrichment
Vulnrichment
•added 2026/04/03 9:41 p.m.•13 views

CVE-2026-28797 RAGFlow: Server-Side Template Injection (SSTI) leading to Remote Code Execution (RCE) in Agent "Text Processing" Component

RAGFlow is an open-source RAG Retrieval-Augmented Generation engine. In versions 0.24.0 and prior, a Server-Side Template Injection SSTI vulnerability exists in RAGFlow's Agent workflow Text Processing StringTransform and Message components. These components use Python's jinja2.Template unsandbox...

8.7CVSS6.5AI score0.00583EPSS
SaveExploits2References1
NVD
NVD
•added 2025/12/15 5:15 p.m.•23 views

CVE-2025-66435

An SSTI Server-Side Template Injection vulnerability exists in the getcontracttemplate method of Frappe ERPNext through 15.89.0. The function renders attacker-controlled Jinja2 templates contractterms using frappe.rendertemplate with a user-supplied context doc. Although Frappe uses a custom...

4.3CVSS0.00361EPSS
SaveExploits1References2
Snyk
Snyk
•added 2025/12/02 6:26 a.m.•6 views

Arbitrary Code Injection

Overview agentc is a The front-facing package for the Couchbase Agent Catalog project. Affected versions of this package are vulnerable to Arbitrary Code Injection due to unsafe rendering of Jinja templates without automatic escaping. The Jinja environment is initialized without autoescape=True,...

9.8CVSS7.7AI score
SaveExploits0References3
CNNVD
CNNVD
•added 2021/02/26 12:00 a.m.•31 views

Saltstack SaltStack Salt: Code Injection Vulnerability

SaltStack Salt is a set of open source tools for managing infrastructure from SaltStack Saltstack. The tool provides configuration management, remote execution, and other features. A code injection vulnerability exists in SaltStack Salt versions prior to Salt 3002.5 that stems from a failure of t...

9.8CVSS7.4AI score0.10426EPSS
SaveExploits0References20
Rows per page
Query Builder