Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions 0.18.0 through 0.19.x are affected when the extract_hidden_states speculative decoding method is configured. A single request that sets a sampling penalty parameter (repetition_penalty, frequency_penalty, or presence_penalty) makes the EngineCore process crash with a RuntimeError, which takes the server out of service. Upgrade to vLLM 0.20.0 or later. If upgrading is not possible, avoid extract_hidden_states as the speculative decoding method, or strip penalty parameters from requests at a gateway.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 6.5 | Medium | 3.1 | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0037, the 30th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:34 UTC First seen by agentprime
- 31 Oct 2026, 14:34 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-83vm-p52w-f9pw
- OSV: GHSA-83vm-p52w-f9pw
- github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw
- nvd.nist.gov/vuln/detail/CVE-2026-44223
- github.com/vllm-project/vllm/pull/38610
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-145.yaml
- github.com/vllm-project/vllm