{"items":[{"id":"NVI-00016206","kind":"vulnerability","title":"vLLM: OOM Denial of Service via Audio Decompression Bomb","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-6pr9-rp53-2pmc","CVE-2026-54233"],"plain_summary":"GitHub lists this reviewed advisory for vllm. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-456dc1f120cdb1c033b370ab1c8bf514"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"CVSS","as_of":"2026-07-17T16:39:17.000Z","value":"6.5 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-456dc1f120cdb1c033b370ab1c8bf514"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-456dc1f120cdb1c033b370ab1c8bf514","url":"https://github.com/advisories/GHSA-6pr9-rp53-2pmc","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-6pr9-rp53-2pmc","publisher":"GitHub Advisory Database","observed_at":"2026-11-04T09:59:26.779Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-456dc1f120cdb1c033b370ab1c8bf514"],"technology":"vllm","known_exclusions":[],"conditions_summary":"### 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 a","public_affected_ranges":["<= 0.23.0"]}],"null_published_at":"2026-11-04T10:04:27.918Z","source_updated_at":"2026-07-17T16:39:17.000Z","source_disclosed_at":"2026-06-17T14:06:22.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-04T09:59:26.779Z"}],"next_cursor":null,"snapshot_revision":"42594"}