{"id":"CVE-2026-57173","aliases":[],"url":"https://o3.security/vulnerability/CVE-2026-57173","summary":"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…","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.","published":"2026-09-16T17:17:24.603","modified":"2026-09-16T17:17:24.603","cvss":{"score":6.5,"severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H"},"epss":null,"cisaKev":null,"exploitsKnown":null,"affectedPackages":[],"fix":{"url":"https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e","label":"vllm-project/vllm@3d20275"},"references":[{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/pull/45908"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr"}],"provenance":{"sources":["OSV.dev","NVD","FIRST.org (EPSS)"],"lastVerified":"2026-09-16T17:17:24.603"}}