CVE-2026-105759: vllm · Uncontrolled Resource Consumption
Affects vllmSource CVE Database V5
Not known to be exploited · CVSS 5.9 Medium : upgrade to 0.30.0 when convenient.
Data as of 17 Nov 2026, 20:25 UTC
- EPSS
- 0.4% chance of exploitation in 30 days – higher than 35% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 0.30.0
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:HExploitation evidence
Disclosed: evidence found.
CVE published 5 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 17 Nov 2026.
What to do
Upgrade vllm and github/vllm-project/vllm to 0.30.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| vllm-projectvllm | Affected
| Fixed in
|
crates.iogithub/vllm-project/vllmpkg:cargo/github/vllm-project/vllmOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
Upgrade to vllm version 0.30.0 or later, where this issue is fixed. Prior versions are vulnerable. No other mitigations or workarounds are indicated in the available data.
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
- github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48 (opens in a new tab)
- github.com/vllm-project/vllm/pull/56058 (opens in a new tab)
- github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352 (opens in a new tab)
- github.com/vllm-project/vllm/releases/tag/v0.30.0 (opens in a new tab)