Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vLLM package, versions >=0.19.0 and <0.26.0, accepts a list of prompts in the /v1/completions endpoint with no limit on the number of prompts, so one request can create one backend engine request per list entry. An authenticated API client can send such a request to consume CPU, memory, scheduling and response-buffer resources in proportion to the list length, which can disrupt other tenants on the same server. Upgrade to vLLM 0.26.0 or later, which is listed as the fixed version.
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 0.0058, the 48th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:29 UTC First seen by agentprime
- 31 Oct 2026, 14:29 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-87x5-vmc3-756j
- OSV: GHSA-87x5-vmc3-756j
- github.com/vllm-project/vllm/security/advisories/GHSA-87x5-vmc3-756j
- nvd.nist.gov/vuln/detail/CVE-2026-73559
- github.com/vllm-project/vllm/pull/47845
- github.com/vllm-project/vllm/commit/675f4295cdfe0d870471c2b51bfeca3a68a9569e
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.26.0