vllm: Use of Uninitialized Resource
CVE-2026-116180 is a high-severity use of uninitialized resource vulnerability in vllm from Vllm-project, with a CVSS 3.1 base score of 7.7 out of 10. It can be exploited remotely over the network by an attacker with a low-privileged account, without any action from a user. The record lists version 0.31.0 as the first without the flaw, so updating vllm to that release or later removes the exposure. There is no confirmed exploitation so far. EPSS estimates a 0.25% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Update vllm to 0.31.0 or a later version.
- Read the advisory on github.com for workarounds and exact fixed builds.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| Vllm-project | vllm | 0.8.5 up to, but not including, 0.31.0 | 0.31.0 |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- LowA basic user account is enough.
- User interaction
- NoneNo action by a victim is required.
- Scope
- ChangedThe attack can reach beyond the vulnerable component into other systems.
- Confidentiality
- NoneNo data is disclosed.
- Integrity
- NoneNothing can be modified.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H. Scored by CNA (vulncheck.com).
| Scoring system | Score | Severity | Scored by |
|---|---|---|---|
| CVSS 4.0 | 8.3 | High | CNA (vulncheck.com) |
| CVSS 3.1 | 7.7 | High | CNA (vulncheck.com) |
Official description
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Use of Uninitialized Resource
The product uses or accesses a resource that has not been initialized.
How developers prevent this class of flaw
- Explicitly initialize the resource before use. If this is performed through an API function or standard procedure, follow all required steps.
- Pay close attention to complex conditionals that affect initialization, since some branches might not perform the initialization.
- Avoid race conditions (CWE-362) during initialization routines.
More Use of Uninitialized Resource vulnerabilities (CWE-908)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: partial).
- Record last changed materially (score, affected products, status or references).
References
Advisories
Third-party and government advisories
Other vulnerabilities in vllm
- 7.5 High severity
- 9.8 Critical severity
- 8.8 High severity
- 7.5 High severity
- 7.5 High severity
- 7.5 High severity
Recent Use of Uninitialized Resource vulnerabilities
- 8.8 High severity
- 8.8 High severity
- 8.8 High severity
- 8.8 High severity
- 8.8 High severity
- 9.6 Critical severity
Spotted an error? Tell us.