Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vLLM OpenAI-compatible HTTP server (PyPI package vllm, versions before 0.32.0) defaults its CORS allowed origins to any origin and performs no authentication unless an API key is configured. A malicious web page on any origin can, through a victim's browser that can reach the server (such as localhost or an internal address), enumerate models, send chat completion requests, and read the responses, though requests carrying credentials are blocked by default. Upgrade vllm to 0.32.0 or later, which contains the fix.
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 |
|---|---|---|---|---|
| 3.4 | Low | 3.1 | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0024, the 15th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 26 Oct 2026, 17:20 UTC Confirmed by the CVE List
- 31 Oct 2026, 14:07 UTC First seen by agentprime
- 31 Oct 2026, 14:07 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-vvpg-rrww-wpmh
- OSV: GHSA-vvpg-rrww-wpmh
- github.com/vllm-project/vllm/security/advisories/GHSA-vvpg-rrww-wpmh
- nvd.nist.gov/vuln/detail/CVE-2026-115917
- github.com/vllm-project/vllm/pull/61009
- github.com/vllm-project/vllm/commit/fcae5c98870ff2c20659731dce7ba3a3ff0d48aa
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.32.0