- CVSS
- MEDIUM · 5.9v3.1CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
- Published
- 2026-10-05
- Weakness
- CWE-400
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-105759
Description
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend’s track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus’s Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.
References
- https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352
- https://github.com/vllm-project/vllm/pull/56058
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0
- https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48
- https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-105759 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.