CVE-2025-61620: vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server

October 7, 2025

A resource-exhaustion (denial-of-service) vulnerability exists in multiple endpoints of the OpenAI-Compatible Server due to the ability to specify Jinja templates via the chat_template and chat_template_kwargs parameters. If an attacker can supply these parameters to the API, they can cause a service outage by exhausting CPU and/or memory resources.

References

github.com/advisories/GHSA-6fvq-23cw-5628
github.com/vllm-project/vllm
github.com/vllm-project/vllm/commit/7977e5027c2250a4abc1f474c5619c40b4e5682f
github.com/vllm-project/vllm/pull/25794
github.com/vllm-project/vllm/security/advisories/GHSA-6fvq-23cw-5628
nvd.nist.gov/vuln/detail/CVE-2025-61620

Code Behaviors & Features

Detect and mitigate CVE-2025-61620 with GitLab Dependency Scanning

Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →