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. Dependency Scanning using SBOM also detects vulnerabilities from proprietary advisories that this site does not include. Learn more about Dependency Scanning using SBOM →