CVE-2026-54233: vLLM Denial of Service Vulnerability

MODERATE
Advisory Identifier: GHSA-6pr9-rp53-2pmc
Share
CVSS 6.5
CWE-409
Published
Advisory Summary

CVE-2026-54233 is a MODERATE (CVSS 6.5) denial of service vulnerability (CWE-409: Improper Handling of Highly Compressed Data (Data Amplification)) affecting vLLM libraries in the PyPI ecosystem. The issue involves oom denial of service via audio decompression bomb. Remediation is available by upgrading affected packages to version 0.24.0.

CVE-2026-54233 at a Glance

CVE Identifier CVE-2026-54233
GHSA Identifier GHSA-6pr9-rp53-2pmc
Severity MODERATE
CVSS v3.1 Base Score 6.5
CWE Classification CWE-409: Improper Handling of Highly Compressed Data (Data Amplification)
Affected Product vLLM
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 6.5

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required Low (PR:L)
User Interaction None (UI:N)
Scope Unchanged (S:U)
Confidentiality None (C:N)
Integrity None (I:N)
Availability High (A:H)

How to Fix CVE-2026-54233

To remediate this vulnerability, upgrade all affected vLLM dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

vllm fixed: 0.24.0 
pip install vllm>=0.24.0
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release: 

pip show vllm

How to Check if You Are Affected

To determine whether your Python environment is affected by CVE-2026-54233, inspect your installed packages using pip:

pip show vllm

Analyze the terminal output to locate any version of vLLM in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 0.24.0), your application is affected.

Note: The pip show vllm command checks currently installed packages in your active Python environment.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-409: Improper Handling of Highly Compressed Data (Data Amplification), where the product does not handle or incorrectly handles a compressed input with a very high compression ratio that produces a large output. In vLLM, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

### 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: ```python # 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 vLLM. ### Fix A fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/44970

CVE-2026-54233 Affected vLLM Versions

1 component(s)
Fixed Versions:
0.24.0
Product / Package Ecosystem Affected Versions Fixed Version
vllm
pypi/vllm
PyPI
< 0.24.0
0.24.0

References

GitHub Advisory / Wiki ADVISORY
https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc
NVD — CVE-2026-54233 NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-54233
vLLM Source Repository REPOSITORY
https://github.com/vllm-project/vllm/pull/44970
Security Fix Commit FIX COMMIT
https://github.com/vllm-project/vllm/commit/1b1359c33269446f13c05da9a90c25174cbea590
GitHub Advisory / Wiki ADVISORY
https://github.com/advisories/GHSA-6pr9-rp53-2pmc
vLLM Source Repository REPOSITORY
https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3404.yaml
vLLM Source Repository REPOSITORY
https://github.com/vllm-project/vllm
vLLM Release RELEASE
https://github.com/vllm-project/vllm/releases/tag/v0.23.1rc0
pypi.org/project/vllm WEB
https://pypi.org/project/vllm

Frequently Asked Questions

What is CVE-2026-54233?
CVE-2026-54233 is a security vulnerability in vLLM involving OOM Denial of Service via Audio Decompression Bomb under CWE-409: Improper Handling of Highly Compressed Data (Data Amplification).
Which vLLM versions are affected?
Affected versions include releases prior to 0.24.0 across affected packages: vllm.
What version fixes CVE-2026-54233?
Upgrading to 0.24.0 (or the latest patched release for your respective branch) resolves the vulnerability.
Is vllm affected?
Yes, vllm is affected in releases prior to 0.24.0. Upgrade your dependency to 0.24.0 or later.
What is the CVSS score of CVE-2026-54233?
CVE-2026-54233 has a CVSS v3.1 base score of 6.5 (MODERATE) with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
What CWE is associated with CVE-2026-54233?
CVE-2026-54233 is classified under CWE-409: Improper Handling of Highly Compressed Data (Data Amplification) (The product does not handle or incorrectly handles a compressed input with a very high compression ratio that produces a large output.).
How can I check PyPI dependencies for CVE-2026-54233?
Run the dependency tree command: 'pip show vllm'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
View Raw JSON 
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-6pr9-rp53-2pmc",
  "modified" : "2026-07-17T16:39:16Z",
  "published" : "2026-06-17T14:06:22Z",
  "aliases" : [ "CVE-2026-54233" ],
  "summary" : "vLLM: OOM Denial of Service via Audio Decompression Bomb",
  "details" : "### 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 after the full decode and does not prevent the allocation.\n\n### Impact\nAn 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 vLLM.\n\n### Fix\n\nA fix for this vulnerability was merged here: https://github.com/vllm-project/vllm/pull/44970",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "vllm"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "0.24.0"
      } ]
    } ],
    "database_specific" : {
      "last_known_affected_version_range" : "<= 0.23.0"
    }
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/security/advisories/GHSA-6pr9-rp53-2pmc"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-54233"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/pull/44970"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/commit/1b1359c33269446f13c05da9a90c25174cbea590"
  }, {
    "type" : "ADVISORY",
    "url" : "https://github.com/advisories/GHSA-6pr9-rp53-2pmc"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-3404.yaml"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/vllm-project/vllm"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/releases/tag/v0.23.1rc0"
  }, {
    "type" : "WEB",
    "url" : "https://pypi.org/project/vllm"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-409" ],
    "severity" : "MODERATE",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-06-17T14:06:22Z",
    "nvd_published_at" : "2026-06-22T23:16:31Z"
  }
}