Vulnerability 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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.16.0, < 0.32.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/commit/cff08b461e086523cee8bba5bd3c66d30262Patch
- https://github.com/vllm-project/vllm/pull/50300Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.32.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-x567-49g5-p4cfPatchVendor Advisory
FAQ
What is CVE-2026-115918?
CVE-2026-115918 is a vulnerability with a CVSS score of 6.5 (MEDIUM). 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_...
How severe is CVE-2026-115918?
CVE-2026-115918 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-115918?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.