CVE-2026-116174: vllm · Improper Input Validation
Affects vllm-project vllmSource CVE Database V5
Not known to be exploited · CVSS 8.2 High.
Data as of 10/25/2026, 16:50:55 UTC
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:NExploitation evidence
Disclosed: evidence found.
CVE published 25 Oct 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wild: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq 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 2026-10-25.
What to do
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
Until a fix is available, avoid exposing the vulnerable services to untrusted inputs or implement input validation controls to block out-of-vocabulary token IDs.
Description
vLLM versions from 0.22.0 up to but not including 0.24.0 have an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream services. This flaw allows attackers to submit out-of-vocabulary prompt token IDs, causing a fatal embedding lookup failure that terminates the EngineCore process and leaves the server in an unhealthy state.
Impact
Successful exploitation results in termination of the EngineCore process and leaves the vLLM server unhealthy, potentially causing denial of service. There is no indication of privilege escalation, data disclosure, or remote code execution from the provided data.