CVE-2026-116180
Description
A flaw was found in vLLM. A remote client sharing the inference engine can trigger a Denial of Service (DoS) by submitting requests with prompt log probabilities enabled against a cached prefix. Because uninitialized memory is allocated for log probability tensors, cached token positions remain unpopulated, causing the tokenizer to encounter invalid values during decoding. This causes an overflow error that crashes the core engine process and terminates all concurrent tenant requests.
Statement
This vulnerability is rated as Moderate severity because exploitation requires network or authenticated access to the inference service and specifically affects configurations utilizing external KV cache transfer connectors. In environments relying solely on standard local prefix caching, the vulnerable code path is not triggered. An attacker sending queries requesting prompt log probabilities against externally cached prefixes can cause the core engine process to terminate unexpectedly, resulting in a denial of service for concurrent users without compromising system confidentiality or data integrity.
Common Vulnerability Scoring System (CVSS) Score Details
Info alert:Important note
CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).
CVSS v3 Score Breakdown
| Red Hat | NVD | cve.org | |
|---|---|---|---|
| Base Score | 6.5 | N/A | 7.7 |
| Attack Vector | Network | N/A | Network |
| Attack Complexity | Low | N/A | Low |
| Privileges Required | Low | N/A | Low |
| User Interaction | None | N/A | None |
| Scope | Unchanged | N/A | Changed |
| Confidentiality | None | N/A | None |
| Integrity Impact | None | N/A | None |
| Availability Impact | High | N/A | High |
Vector
Red Hat: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
cve.org: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H
Understanding the Weakness (CWE)
Confidentiality
Technical Impact: Read Memory; Read Application Data
When reusing a resource such as memory or a program variable, the original contents may not have been cleared before it is sent to an untrusted party.
Availability
Technical Impact: DoS: Crash, Exit, or Restart; DoS: Instability
The uninitialized resource may contain values that cause program flow to change in ways that the programmer did not intend, possibly leading to a crash.
Other
Technical Impact: Unexpected State; Varies by Context
The consequences vary depending on the type of resource and how it is used within the product.
Frequently Asked Questions
Not sure what something means? Check out our Security Glossary.
Want to get errata notifications? Sign up here.
