Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vllm versions up to and including 0.19.0 contain an improper resource shutdown or release flaw in the OpenAI-compatible serving path. A remote attacker can trigger it to cause a denial of service, and a public exploit is reported to exist. The source gives few details, and no fixed version is listed.
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 |
|---|---|---|---|---|
| 6.9 | Medium | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P | CNA (VulDB) |
- CISA KEV Not listed.
- EPSS 0.0043, the 37th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 15:02 UTC First seen by agentprime
- 31 Oct 2026, 15:02 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-98f3-hwg4-4rf7
- OSV: GHSA-98f3-hwg4-4rf7
- nvd.nist.gov/vuln/detail/CVE-2026-9540
- github.com/vllm-project/vllm/issues/37343
- github.com/vllm-project/vllm/pull/37594
- github.com/vllm-project/vllm
- ingero.io/debugging-vllm-latency-minimax-ollama-mcp
- vuldb.com/submit/814645
- vuldb.com/vuln/365601
- vuldb.com/vuln/365601/cti