CVE-2026-5497: Vllm Denial of Service Vulnerability

HIGH
Advisory Identifier: GHSA-wcwg-c5fc-9vrc
Share
CVSS 7.5
CWE-400 CWE-770
Published
Advisory Summary

CVE-2026-5497 is a HIGH (CVSS 7.5) denial of service vulnerability (CWE-400: Uncontrolled Resource Consumption) affecting Vllm libraries in the PyPI ecosystem. The issue involves vllm is vulnerable to an out-of-memory (oom) denial of service (dos) attack due to unbounded frame count processing in the `videomediaio.load_base64()` method. Remediation is available by upgrading affected packages to version 0.19.0.

CVE-2026-5497 at a Glance

CVE Identifier CVE-2026-5497
GHSA Identifier GHSA-wcwg-c5fc-9vrc
Severity HIGH
CVSS v3.1 Base Score 7.5
CWE Classification CWE-400: Uncontrolled Resource Consumption
Affected Product Vllm
Package Ecosystem PyPI
Published Date
Last Updated

Security Impact

CVSS: 7.5

The security impact metrics below are parsed directly from the CVSS v3.1 vector string (CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H).

Attack Vector Network (AV:N)
Attack Complexity Low (AC:L)
Privileges Required None (PR:N)
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-2026-5497

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: 0.19.0 
pip install vllm>=0.19.0
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-2026-5497, 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 0.19.0), 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-400: Uncontrolled Resource Consumption, where the product does not properly control the allocation and maintenance of a limited resource. 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

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

CVE-2026-5497 Affected Vllm Versions

1 component(s)
Fixed Versions:
0.19.0
Product / Package Ecosystem Affected Versions Fixed Version
vllm
pypi/vllm
PyPI
≥ 0.8.0
< 0.19.0
0.19.0

References

NVD — CVE-2026-5497 NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-5497
Security Fix Commit FIX COMMIT
https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
access.redhat.com/errata/rhsa-2026:33... WEB
https://access.redhat.com/errata/RHSA-2026:33524
access.redhat.com/errata/rhsa-2026:33... WEB
https://access.redhat.com/errata/RHSA-2026:33531
Vllm Security Information SECURITY
https://access.redhat.com/security/cve/CVE-2026-5497
bugzilla.redhat.com/show_bug.cgi WEB
https://bugzilla.redhat.com/show_bug.cgi?id=2487813
Vllm Source Repository REPOSITORY
https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2302.yaml
Vllm Source Repository REPOSITORY
https://github.com/vllm-project/vllm
huntr.com/bounties/7bd92629-b... WEB
https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
Vllm Security Information SECURITY
https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json

Frequently Asked Questions

What is CVE-2026-5497?
CVE-2026-5497 is a security vulnerability in Vllm involving vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method under CWE-400: Uncontrolled Resource Consumption.
Which Vllm versions are affected?
Affected versions include releases prior to 0.19.0 across affected packages: vllm.
What version fixes CVE-2026-5497?
Upgrading to 0.19.0 (or the latest patched release for your respective branch) resolves the vulnerability.
Is vllm affected?
Yes, vllm is affected in releases prior to 0.19.0. Upgrade your dependency to 0.19.0 or later.
What is the CVSS score of CVE-2026-5497?
CVE-2026-5497 has a CVSS v3.1 base score of 7.5 (HIGH) with vector string CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H.
What CWE is associated with CVE-2026-5497?
CVE-2026-5497 is classified under CWE-400: Uncontrolled Resource Consumption (The product does not properly control the allocation and maintenance of a limited resource.).
How can I check PyPI dependencies for CVE-2026-5497?
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-wcwg-c5fc-9vrc",
  "modified" : "2026-08-18T20:16:47Z",
  "published" : "2026-06-11T12:32:44Z",
  "aliases" : [ "CVE-2026-5497" ],
  "summary" : "vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method",
  "details" : "vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "vllm"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0.8.0"
      }, {
        "fixed" : "0.19.0"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2026-5497"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:33524"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/errata/RHSA-2026:33531"
  }, {
    "type" : "WEB",
    "url" : "https://access.redhat.com/security/cve/CVE-2026-5497"
  }, {
    "type" : "WEB",
    "url" : "https://bugzilla.redhat.com/show_bug.cgi?id=2487813"
  }, {
    "type" : "WEB",
    "url" : "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2302.yaml"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/vllm-project/vllm"
  }, {
    "type" : "WEB",
    "url" : "https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4"
  }, {
    "type" : "WEB",
    "url" : "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-400", "CWE-770" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-08-18T20:16:47Z",
    "nvd_published_at" : "2026-06-11T10:16:21Z"
  }
}