All vulnerabilities

Servers and applications

CVE-2026-105759

Unbounded Prometheus label cardinality from attacker-controlled HTTP method tokens in the vLLM Rust frontend metrics middleware (unauthenticated denial of service)

Severity
High 7.5
Published
23 Sept 2026
Last changed
16 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.30.0
Exploit chance
0.4% in the next 30 daysHigher than 36% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Uncontrolled resource consumption (CWE-400)
Attack
Over the network · No login needed · No user action needed
Attacker can
Take it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Also known as
GHSA-5fj9-pfhr-6j48
Sources
NVD, CVE Program, Project advisories (GitHub)

Description

attachment.zip

The Rust frontend of vLLM (vllm-rs, enabled via VLLM_USE_RUST_FRONTEND=1 or by running the vllm-rs binary directly) records Prometheus HTTP metrics in the middleware track_http_metrics. It uses the raw HTTP method token of each request (req.method().as_str()) as a Prometheus label value, with no method allowlist, no label normalization, and no cardinality cap. An unauthenticated remote attacker can send requests with unique, arbitrary method tokens (e.g. XVULNCARD000001 /tokenize HTTP/1.1) to any registered route; the request is answered with 405 by axum's method router but still flows through the metrics middleware, permanently inserting new label sets into the global http_requests counter family and http_request_duration_seconds histogram family. Memory grows unboundedly until the process is OOM-killed, and every /metrics scrape becomes larger and more expensive to render.

From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cna:vllm-project|vllm
  • Every version before 0.30.0
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.30.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.30.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-105759
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-105759
  • GitHub Advisory Database https://github.com/advisories/GHSA-5fj9-pfhr-6j48
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48