CVE-2026-57173

medium

Assigned by CNA: github_m

Published 2026-09-16 · Modified 2026-09-16

Discuss on Community Propose mitigation

CVSS v3

6.5

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H

CVSS v4 NEW

—

not yet in upstream

VIR risk

6.5

Description

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.

Predictions

Exploit likelihood

75%

Patch ETA

—

Heuristic predictions, AS-IS, for prioritization only.

Mitigations

No mitigations published for this CVE yet.

The vendor-content worker queues fetches as references arrive (check back in a few minutes). Or — if you've already worked around this in production — publish your fix to the community-verified tier.

Propose a mitigation on Community Mitigations published via the community go through AI scoring + 2 human reviewers + 7-day silent objection window before landing here with source_tier=community-verified.

References

CWEs

CWE-770

Community-verified mitigations for this CVE will appear above when contributors publish them.

Verify integrity in audit chain (admin only). AS-IS.