CVE-2026-105759
5.9 MEDIUMpublic exploit availablePublished 2026-10-05 · Updated 2026-10-06
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD 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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H
Weaknesses
CWE-400
Public exploit & PoC 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
All 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
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2026-100137
- HIGHCVE-2026-100138
- HIGHCVE-2026-100139
- HIGHCVE-2026-100242PoC
- MEDIUMCVE-2026-100350PoC
- MEDIUMCVE-2026-100527PoC
- LOWCVE-2026-100542PoC
- HIGHCVE-2026-100558PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.