Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions 0.22.0 up to but not including 0.24.0 read the entire uploaded file for the /v1/audio/transcriptions and /v1/audio/translations routes into memory before checking the documented audio file-size limit. An API caller who can reach these endpoints, including with any required API key, can send an oversized file and force memory allocation proportional to its size, which can exhaust memory or crash the process (availability impact only). Upgrade to vLLM 0.24.0 or later. Reverse-proxy or ASGI body-size limits can reduce exposure in the meantime.
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 0.0052, the 44th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:42 UTC First seen by agentprime
- 31 Oct 2026, 14:42 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-v82g-2437-67m2
- OSV: GHSA-v82g-2437-67m2
- github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2
- nvd.nist.gov/vuln/detail/CVE-2026-55646
- github.com/vllm-project/vllm/pull/45510
- github.com/vllm-project/vllm/commit/b997071ec493765abbed990c65843ed05e4708a8
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2305.yaml
- github.com/vllm-project/vllm