{"id":"CVE-2026-54233","aliases":["GHSA-6pr9-rp53-2pmc","PYSEC-2026-3404"],"url":"https://o3.security/vulnerability/CVE-2026-54233","summary":"vLLM: OOM Denial of Service via Audio Decompression Bomb","details":"### Summary\nvLLM's `/v1/audio/transcriptions` endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. Tested on vLLM v0.19.0.\n\n### Details\n`SpeechToTextProcessor` rejects uploads over `VLLM_MAX_AUDIO_CLIP_FILESIZE_MB` (default 25MB) based on compressed byte length, but the audio decoder in `audio.py` accumulates all decoded frames into memory with no size limit before returning:\n\n```python\n# speech_to_text.py L184-189\nif len(audio_data) / 1024 ** 2 > self.max_audio_filesize_mb:\n    raise VLLMValidationError(...)\ny, sr = load_audio(buf, sr=self.asr_config.sample_rate)  # decoded size unchecked\n\n# audio.py L77-107\nchunks: list[npt.NDArray] = []\nfor frame in container.decode(stream):\n    chunks.append(frame.to_ndarray())\naudio = np.concatenate(chunks, axis=-1).astype(np.float32)  # single contiguous allocation\n```\n\nA 25MB OPUS file at 6kbps encodes ~8.7 hours of audio. Decoding produces ~5.7GB of float32 PCM (232x amplification), and `np.concatenate` then allocates a second contiguous array, bringing peak RSS to ~14.9GB from a single request. `SpeechToTextConfig.max_audio_clip_s` (default 30s) applies only after the full decode and does not prevent the allocation.\n\n### Impact\nAn unauthenticated attacker can exhaust server memory with a small number of concurrent requests, each a valid upload within the documented size limit. Severity was assessed with reference to prior OOM vulnerability reports in vLLM.\n\n### Fix\n\nA fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/44970","published":"2026-06-22T22:10:45.689Z","modified":"2026-10-21T02:58:32.460923092Z","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":{"score":0.00422,"percentile":0.35671,"asOf":"2026-09-12"},"cisaKev":null,"exploitsKnown":0,"affectedPackages":[{"ecosystem":"PyPI","name":"vllm","fixedVersion":"0.24.0"}],"fix":{"url":"https://github.com/vllm-project/vllm/pull/44970","label":"vllm-project/vllm#44970"},"references":[{"type":"ADVISORY","url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54233.json"},{"type":"ADVISORY","url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc"},{"type":"ADVISORY","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-54233"},{"type":"FIX","url":"https://github.com/vllm-project/vllm/pull/44970"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/commit/1b1359c33269446f13c05da9a90c25174cbea590"},{"type":"ADVISORY","url":"https://github.com/advisories/GHSA-6pr9-rp53-2pmc"},{"type":"WEB","url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3404.yaml"},{"type":"PACKAGE","url":"https://github.com/vllm-project/vllm"},{"type":"WEB","url":"https://github.com/vllm-project/vllm/releases/tag/v0.23.1rc0"},{"type":"WEB","url":"https://pypi.org/project/vllm"}],"provenance":{"sources":["OSV.dev","FIRST.org (EPSS)"],"lastVerified":"2026-10-21T02:58:32.460923092Z"}}