CVE-2026-115918
Last modified
CVE-2026-115918 is a medium-severity vulnerability rated 6.5/10 on the CVSS scale. 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_kwargs[chat_template] when no server template is configured.
Description
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_kwargs[chat_template] when no server template is configured. ChatParams.get_apply_chat_template_kwargs() preserves that value without enforcing trust_request_chat_template, so the request can bypass the intended trust policy and cause CPU or memory exhaustion through Jinja rendering. This issue is fixed in version 0.32.0.
Metrics
Weakness Enumeration
Affected Software
Source: CNA advisory (CVE.org). NVD analysis pending.
| Vendor | Product | Versions |
|---|---|---|
| vllm-project | vllm | >= 0.16.0, < 0.32.0 |
References
Timeline
- Published
- Last Modified
- Status
- Awaiting Analysis
Frequently Asked Questions
What is CVE-2026-115918?
How severe is CVE-2026-115918?
How do I fix CVE-2026-115918?
How Strix Helps
- How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
- Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
- PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
- AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.
Related CVEs from 2026
- CVE-2026-115912vLLM is an inference and serving engine for large language m…7.5
- CVE-2026-115913vLLM is an inference and serving engine for large language m…6.5
- CVE-2026-115914vLLM is an inference and serving engine for large language m…6.5
- CVE-2026-115915vLLM is an inference and serving engine for large language m…8.1
- CVE-2026-115916vLLM is an inference and serving engine for large language m…6.5
- CVE-2026-115917vLLM is an inference and serving engine for large language m…3.4
- CVE-2026-115919Open Neural Network Exchange (ONNX) is an open standard for …6.2
- CVE-2026-11592The Email Subscribers & Newsletters – Email Marketing, Post …4.3
- CVE-2026-115920Open Neural Network Exchange (ONNX) is an open standard for …6.2
- CVE-2026-115921Open Neural Network Exchange (ONNX) is an open standard for …6.2
- CVE-2026-115922Open Neural Network Exchange (ONNX) is an open standard for …6.2
- CVE-2026-115923Backstage is an open framework for building developer portal…6.5
Are you affected by CVE-2026-115918?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
