CVE-2026-57173
- Source
- https://cve.org/CVERecord?id=CVE-2026-57173
- Import Source
- https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-57173.json
- JSON Data
- https://api.osv.dev/v1/vulns/CVE-2026-57173
- Aliases
- Downstream
- Published
- 2026-09-16T16:34:39Z
- Modified
- 2026-09-20T11:30:51Z
- Severity
-
- 6.5 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CVSS Calculator
- Summary
- vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
- Details
-
vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0.
- Database specific
{ "cna_assigner": "GitHub_M", "cwe_ids": [ "CWE-770" ], "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/57xxx/CVE-2026-57173.json" }- References
-
- https://github.com/vllm-project/vllm/releases/tag/v0.24.0
- https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/57xxx/CVE-2026-57173.json
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr
- https://nvd.nist.gov/vuln/detail/CVE-2026-57173
- https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e
- https://github.com/vllm-project/vllm/pull/45908