All vulnerabilities

Servers and applications

CVE-2026-57173

Unauthenticated audio decompression-bomb DoS in /v1/chat/completions: VLLM_MAX_AUDIO_DECODE_DURATION_S guard not wired into the chat audio path (sibling of CVE-2026-5497)

Severity
Medium 6.5
Published
23 Aug 2026
Last changed
7 Oct 2026
Added to UpHeron
3 Nov 2026
Fixed in
0.24.0
Exploit chance
0.7% in the next 30 daysHigher than 55% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Allocation without limits (CWE-770)
Attack
Over the network · Needs a user account · No user action needed
Attacker can
Take it down
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Also known as
GHSA-hcwq-8wjf-3gcr
Sources
NVD, Project advisories (GitHub)

Description

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.

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)
From vllm-project/vllm's security advisory. Shortened; the full text is there.

Affected software

SoftwareAffected versions
vLLMServers and applications · cpe:a:vllm:vllm
  • Every version before 0.24.0
vLLMServers and applications · github:vllm-project/vllm
  • Every version before 0.24.0

About vLLM

open-source software for large language model inference

From Wikidata, CC0 1.0.
Docker Hub pulls
44,195,225Docker Hub, 15 Nov 2026
GitHub stars
96,943GitHub, 15 Nov 2026
Forks
24,836GitHub, 15 Nov 2026
Latest release
v0.33.0rc3GitHub, 15 Nov 2026
Released
2 Nov 2026GitHub
License
Apache Software License 2.0Wikidata
First published on GitHub
9 Feb 2023GitHub

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-57173
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-57173
  • GitHub Advisory Database https://github.com/advisories/GHSA-hcwq-8wjf-3gcr
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr