CVE-2026-90878

Affects: vLLM

CVSS: MEDIUM · 4.3v3.1
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
Published: 2026-09-15
Weakness: CWE-400, CWE-404
Source: nvd.nist.gov/vuln/detail/CVE-2026-90878

Description

A vulnerability was determined in vllm-project vLLM up to 0.27.1. This affects an unknown part of the file /v1/chat/completions of the component Jinja Template Rendering. This manipulation of the argument chat_template causes resource consumption. The attack can be initiated remotely. The exploit has been publicly disclosed and may be utilized. The pull request to fix this issue awaits acceptance.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-90878 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming