Advisory details:
pypa / vllm/PYSEC-2026-4179
| Advisory ID | pypa/vllm/PYSEC-2026-4179 |
| Aliases |
CVE-2026-57173
GHSA-hcwq-8wjf-3gcr PYSEC-2026-4179 |
| Summary | vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions ### Summary The audio decode-duration guard (`max_duration_s`, env `VLLM_MAX_AUDIO_DECODE_DURATION_S`, default 600s) that protects against audio decompression-bomb DoS is wired into **only** the speech-to-text path (`/v1/audio/transcriptions`). The **chat** audio path (`/v1/chat/completions`, `input_audio` content parts) calls the same decoder with **no** limit, so an **unauthenticated** client can submit a few-KB compressed audio file that expands to multiple GB of float32 PCM at decode time, OOM-killing the worker. This is a distinct sibling of **CVE-2026-5497** (video frame-count bomb, `VideoMediaIO.load_base64`) and **GHSA-pq5c-rjhq-qp7p** (image) in the same media subsystem. Verified against `main` at HEAD `d78650c` (2026-06-16); applicable to the latest release v0.23.0. ### Details The guard rejects long audio *during* decode (before allocation), implemented in `vllm/multimodal/media/audio.py`: - `load_audio_pyav` — metadata reject (~82-98) and live sample-count reject (~129-136) - `load_audio_soundfile` — frames reject (~165-174) All are gated on `if max_duration_s is not None`. It is passed in exactly **one** place — the transcription serving layer: ```python # .../speech_to_text/base/serving.py:~170-174 load_audio(buf, sr=..., max_duration_s=self.max_audio_decode_duration_s) # self.max_audio_decode_duration_s = envs.VLLM_MAX_AUDIO_DECODE_DURATION_S (default 600) ``` The chat path never threads it: ```python # vllm/multimodal/media/audio.py:237-238 def load_bytes(self, data: bytes) -> tuple[npt.NDArray, float]: return load_audio(BytesIO(data), sr=None) # no max_duration_s -> every guard above is skipped ``` Unauthenticated reachability chain (chat): `parse_input_audio` (`chat_utils.py`) -> `parse_audio` -> `connector.fetch_audio` -> `AudioMediaIO._load_data_url` -> `load_base64` -> `load_bytes` -> `load_audio(..., sr=None)`. The connector never passes `max_duration_s`, and inline `data:` URLs need no HTTP fetch (so `VLLM_AUDIO_FETCH_TIMEOUT` does not bound them). The OpenAI-compatible server has no auth by default (auth only when `--api-key` / `VLLM_API_KEY` is set). ### Impact Unauthenticated remote denial of service (availability) via memory amplification on a default-no-auth endpoint, on any deployment serving an audio-capable model. Same class and impact as the sibling CVE-2026-5497 (video). CWE-770 / CWE-409. ### Fix A fix was introduced in this MR: https://github.com/vllm-project/vllm/pull/45908 |
| Status | Published |
| Exploitability | 0.5 |
| Weighted Severity | 5.9 |
| Risk | 3.0 |
| Affected and Fixed Packages | Package Details |
| Introduced and Fixed Package Commit Patches | Package Commit Patches Details |
| There are no known CWE. |
| System | Score | Found at |
|---|---|---|
| cvssv3.1 | 6.5 | https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-4179.yaml |
| Reference id | Reference type | URL |
|---|---|---|
| https://github.com/advisories/GHSA-hcwq-8wjf-3gcr | ||
| https://github.com/vllm-project/vllm | ||
| https://github.com/vllm-project/vllm/releases/tag/v0.24.0 | ||
| https://pypi.org/project/vllm | ||
| 3d20275bb4d434f53055c3c0b645fd8bb072965e | Other | https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e |
| 45908 | Other | https://github.com/vllm-project/vllm/pull/45908 |
| CVE-2026-57173 | https://nvd.nist.gov/vuln/detail/CVE-2026-57173 | |
| GHSA-hcwq-8wjf-3gcr | Other | https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr |
No EPSS data available for this advisory.
| Patch URL | |
|---|---|
| There are no known patches. | |
| Attack Vector (AV) | Attack Complexity (AC) | Privileges Required (PR) | User Interaction (UI) | Scope (S) | Confidentiality Impact (C) | Integrity Impact (I) | Availability Impact (A) |
|---|---|---|---|---|---|---|---|
network adjacent_network local physical |
low high |
none low high |
none required |
unchanged changed |
high low none |
high low none |
high low none |
There are no SSVC decisions available.