Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Unauthenticated remote denial of service in vLLM versions before 0.24.0. The audio decode-duration limit applies only to the speech-to-text endpoint, not to audio sent through /v1/chat/completions. An unauthenticated client can send a small compressed audio file that expands to several gigabytes when decoded, exhausting memory and crashing the worker. Upgrade to vLLM 0.24.0 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 0.0073, the 54th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:09 UTC First seen by agentprime
- 31 Oct 2026, 14:09 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-hcwq-8wjf-3gcr
- OSV: GHSA-hcwq-8wjf-3gcr
- github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr
- nvd.nist.gov/vuln/detail/CVE-2026-57173
- github.com/vllm-project/vllm/pull/45908
- github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/releases/tag/v0.24.0