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
- 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.
Affected software
| Software | Affected versions |
|---|---|
vLLMServers and applications · cna:vllm-project|vllm |
|
vLLMServers and applications · cpe:a:vllm:vllm |
|
vLLMServers and applications · github:vllm-project/vllm |
|
About vLLM
open-source software for large language model inference
- 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
Website Source code Docker image
Vulnerabilities in vLLM
- In our list
- 169
- Published in the last 12 months
- 150
- Critical, last 12 months
- 6
- High, last 12 months
- 63
- Known exploited
- 0
- CVE-2026-130686vLLM 0.6.0 before 0.33.0 Resource Exhaustion via Multi-Image RequestsHigh 8.7 18 Nov 2026
- CVE-2026-130684vLLM before 0.33.0 Path Traversal via speculators_config verifier.name_or_pathMedium 5.3 18 Nov 2026
- CVE-2026-130685vLLM 0.28.0 before 0.33.0 Unauthenticated DoS via Out-of-Range Prompt Token IDHigh 8.7 18 Nov 2026
- GHSA-xgh8-qwjh-q853/v1/systemone bypasses the --trust-request-chat-template gateMedium 6.5 18 Nov 2026
- CVE-2026-129356vllm-project vllm Common Prefix single_type_kv_cache_manager.py race conditionLow 2.3 15 Nov 2026
- CVE-2026-126394vLLM 0.30.0 before 0.31.0 Resource Exhaustion via OpenPangu Video Backend num_framesMedium 6.9 13 Nov 2026
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