Advisory details:
pypa / vllm/PYSEC-2026-4325
| Advisory ID | pypa/vllm/PYSEC-2026-4325 |
| Aliases |
CVE-2026-105759
GHSA-5fj9-pfhr-6j48 PYSEC-2026-4325 |
| Summary | 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. |
| Status | Published |
| Exploitability | 0.5 |
| Weighted Severity | 6.8 |
| Risk | 3.4 |
| Affected and Fixed Packages | Package Details |
| Introduced and Fixed Package Commit Patches | Package Commit Patches Details |
| There are no known CWE. |
| System | Score | Found at |
|---|---|---|
| cvssv3.1 | 7.5 | https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4325.yaml |
No EPSS data available for this advisory.
| Patch URL | |
|---|---|
| There are no known patches. | |
| Attack Vector (AV) | Attack Complexity (AC) | Privileges Required (PR) | User Interaction (UI) | Scope (S) | Confidentiality Impact (C) | Integrity Impact (I) | Availability Impact (A) |
|---|---|---|---|---|---|---|---|
network adjacent_network local physical |
low high |
none low high |
none required |
unchanged changed |
high low none |
high low none |
high low none |
There are no SSVC decisions available.