Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions from 0.11.1 before 0.32.0 that serve DeepSeek-OCR family models (DeepSeek-OCR, DeepSeek-OCR-2, or Unlimited-OCR) can be crashed by one unauthenticated chat request containing an image with a specific pixel distribution, under default configuration. The crash takes down the serving process, and the deployment stays down until it is manually restarted. Upgrade vLLM to 0.32.0 or later.
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 0.0040, the 34th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:07 UTC First seen by agentprime
- 31 Oct 2026, 14:07 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-gq5q-89c7-vhvx
- OSV: GHSA-gq5q-89c7-vhvx
- github.com/vllm-project/vllm/security/advisories/GHSA-gq5q-89c7-vhvx
- nvd.nist.gov/vuln/detail/CVE-2026-115914
- github.com/vllm-project/vllm/pull/59417
- github.com/vllm-project/vllm/commit/c15672cfb49152ebf65cfd188e71b84593ec5686
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.32.0