Sign in Sign up
JA · EN · FR
SecPulse
Categories
CVE-2026-54233 medium CVSS 6.5

Vulnerability in vllm (CVE-2026-54233)

Summary

Vulnerability in vllm (CVE-2026-54233). Risk of unauthorized operations or information disclosure. Exploitable via SpeechToTextProcessor. Mitigation: upgrade to 0.24.0 or later.

Original description

The description as published by the source.

Summary

vLLM'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.

Details

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:

# speech_to_text.py L184-189
if len(audio_data) / 1024 ** 2 > self.max_audio_filesize_mb:
    raise VLLMValidationError(...)
y, sr = load_audio(buf, sr=self.asr_config.sample_rate)  # decoded size unchecked

# audio.py L77-107
chunks: list[npt.NDArray] = []
for frame in container.decode(stream):
    chunks.append(frame.to_ndarray())
audio = np.concatenate(chunks, axis=-1).astype(np.float32)  # single contiguous allocation

A 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.

Impact

An 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 vLL…

Source: GitHub Security Advisories (Global) NVD GitHub Advisory

Auto-generated summary

Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.

A vulnerability tracked as CVE-2026-54233 has been found in vllm.
Attackers can target a specific entry point like SpeechToTextProcessor over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 6.5/10.
What to do: upgrade vllm to 0.24.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-54233" on the vendor's site.

CVE-2026-54233 (vllm) — CWE-409 / CVSS v3 6.5
Attack vector: remote (network-reachable) / no user interaction
Attack surface: SpeechToTextProcessor / VLLM_MAX_AUDIO_CLIP_FILESIZE_MB / audio.py / np.concatenate
Patched: 0.24.0 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.

❓ What is the problem

A vulnerability (CWE-409) exists in vllm. Attackers reach the vulnerable code path via SpeechToTextProcessor.

📍 Affected scope

Check the vendor advisory for the affected versions of vllm. Attack surface: SpeechToTextProcessor / VLLM_MAX_AUDIO_CLIP_FILESIZE_MB / audio.py / np.concatenate.

🔥 Severity

Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.

🔧 How to fix

Update to 0.24.0.

🛡️ Workaround

Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.

🔍 Detection

Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'vllm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.

Response actions

Concrete steps and command examples for SOC/SRE teams to execute in order

  1. 1
    Identify exposure identify 
    grep -r 'vllm' . | grep -v node_modules

    リポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で vllm を grep し、稼働しているサービス・バージョンを把握する。

  2. 2
    Apply patch patch 
    Upgrade vllm to 0.24.0

    ステージング環境で 0.24.0 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。

  3. 3
    Post-deployment verification verify 
    Confirm patched version is live in production

    パッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。

Affected packages

pip vllm
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.24.0"}]}]

References

We use cookies for analytics and ad measurement. This setting applies to all Game co., Ltd. sites. Details