Medium severity5.9NVD Advisory· Published Oct 5, 2026· Updated Oct 16, 2026
CVE-2026-105759
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
2Patches
Vulnerability mechanics
References
4- github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352nvdPatch
- github.com/vllm-project/vllm/pull/56058nvdIssue TrackingPatch
- github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48nvdExploitVendor Advisory
- github.com/vllm-project/vllm/releases/tag/v0.30.0nvdRelease Notes
News mentions
1- VLLM: Batch of 11 Medium-Severity Vulnerabilities Disclosed TogetherVypr Intelligence · Oct 6, 2026