CVE-2026-55646
2 advisories.
PyPI/vllm CVE-2026-55646: medium 6.5
vLLM: Speech-to-text upload size limit is enforced after full UploadFile read
Action: Upgrade vllm to 0.24.0 or later.
pip install vllm==0.24.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0.22.0 | 0.24.0 | - |
Fixed versions
| 0.24.0 |
Sources
- osv: GHSA-v82g-2437-67m2
- https://github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2
- https://nvd.nist.gov/vuln/detail/CVE-2026-55646
- https://github.com/vllm-project/vllm/pull/45510
- https://github.com/vllm-project/vllm/commit/b997071ec493765abbed990c65843ed05e4708a8
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2305.yaml
- https://github.com/vllm-project/vllm
CVE-2026-55646 · published · modified · JSON
PyPI/vllm CVE-2026-55646: medium 6.5
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize a
Action: Upgrade vllm to 0.24.0 or later.
pip install vllm==0.24.0Affected
| introduced | fixed | last affected |
|---|---|---|
| 0.22.0 | 0.24.0 | - |
Fixed versions
| 0.24.0 |
Sources
- osv: PYSEC-2026-2305
- https://github.com/vllm-project/vllm/security/advisories/GHSA-v82g-2437-67m2
- https://github.com/vllm-project/vllm/commit/b997071ec493765abbed990c65843ed05e4708a8
- https://github.com/vllm-project/vllm/pull/45510
CVE-2026-55646 · published · modified · JSON