CVE-2026-116173: 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
|
GitHubvllm-project/vllmpkg: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, restrict or validate input sizes for output_candidates.token_ids in Generate and GenerateStream requests to prevent exceeding 128 entries. Monitor for anomalous requests that attempt to bypass this limit.
Description
vLLM versions from 0.22.0 up to but not including 0.24.0 contain a denial of service vulnerability. Remote attackers can exploit this by sending specially crafted Generate or GenerateStream requests with output_logprobs enabled and more than 128 output_candidates.token_ids. This triggers a fatal sampler exception in the Rust gRPC frontend, causing the EngineCore to crash and resulting in denial of service.
Impact
Successful exploitation results in denial of service by crashing the EngineCore component of vLLM, disrupting availability of the affected service. There is no indication of privilege escalation, data disclosure, or code execution. The attack requires network access and partial control over request parameters.